diff --git a/README.ja.md b/README.ja.md index 870317c..11e369e 100644 --- a/README.ja.md +++ b/README.ja.md @@ -5,7 +5,7 @@

Awesome JEV ギャラリーを見る · 注目プロジェクト · - 全 125 プロジェクト · + 全 147 プロジェクト · JSON カタログ · English · 简体中文 @@ -13,9 +13,9 @@

Awesome JEV

-

GitHub 100★以上・ソース確認済みの JEV 関連プロジェクト／連携／ツール／オープンモデル／実験だけをまとめています。

+

GitHub 50★以上・ソース確認済みの JEV 関連プロジェクト、連携、ツール、オープンモデル、実験、エコシステム資料をまとめています。

-

掲載の中心は 100 stars 以上。JEV が選択・採点・ルーティング・フィルタを担い、実行制御はアプリ側に残る事例です。

+

掲載基準は 50 stars 以上。JEV が選択・採点・ルーティング・フィルタを担い、実行制御はアプリ側に残る事例です。

概要

@@ -31,7 +31,7 @@ - 125 + 147 34 10 2026-09-21 @@ -43,16 +43,16 @@

カテゴリから探す

- ブラウザ・PC 操作 · 3 · - SDK・フレームワーク · 9 · - ルーティング · 4 · - オープンモデル · 8 · - 検索・データ · 4
- 安全性・レビュー · 5 · - Agent ワークフロー · 3 · - UI・自動化 · 3 · - 開発者ツール · 2 · - 業務特化ツール · 3 + ブラウザ・PC 操作 · 14 · + SDK・フレームワーク · 23 · + ルーティング · 14 · + オープンモデル · 17 · + 検索・データ · 9
+ 安全性・レビュー · 12 · + Agent ワークフロー · 11 · + UI・自動化 · 8 · + 開発者ツール · 27 · + 業務特化ツール · 12

## 注目プロジェクト @@ -72,133 +72,156 @@

フィルターと詳しい説明付きで見る →

-## 全 125 プロジェクト - -- [LangChain · TypeSafe](https://github.com/langchain-ai/langchain) · 146,779 stars -- [AI Hedge Fund · JEV Adapter](https://github.com/virattt/ai-hedge-fund) · 63,642 stars -- [LiteLLM · JEV Router](https://github.com/BerriAI/litellm) · 59,305 stars -- [Oh My Pi · JEV Judgments](https://github.com/can1357/oh-my-pi) · 32,236 stars -- [Jev Model Router](https://github.com/davila7/claude-code-templates) · 30,870 stars -- [Composio · TypeSafe Provider](https://github.com/ComposioHQ/composio) · 30,268 stars -- [Vercel AI SDK · TypeSafe](https://github.com/vercel/ai) · 26,870 stars -- [Cua · JEV Use](https://github.com/trycua/cua) · 25,422 stars -- [Openwork](https://github.com/different-ai/openwork) · 23,682 stars -- [Pydantic AI · TypeSafe](https://github.com/pydantic/pydantic-ai) · 20,084 stars -- [Eliza · TypeSafe Client](https://github.com/elizaOS/eliza) · 19,404 stars -- [LangChain.js · TypeSafe](https://github.com/langchain-ai/langchainjs) · 18,215 stars -- [json-render · JEV Compose](https://github.com/vercel-labs/json-render) · 17,731 stars -- [Jev Ultrafast](https://github.com/browser-use/jev-ultrafast) · 13,811 stars -- [QuantDinger · JEV Gate](https://github.com/OpenByteInc/QuantDinger) · 11,883 stars -- [OpenChamber · JEV Router](https://github.com/openchamber/openchamber) · 10,213 stars -- [Rig · TypeSafe Crate](https://github.com/0xPlaygrounds/rig) · 8,691 stars -- [Firstmate · JEV Dispatch](https://github.com/kunchenguid/firstmate) · 6,889 stars -- [Laya](https://github.com/NandhaKishorM/laya) · 6,688 stars -- [Fast Jev Compaction](https://github.com/tamaratran/fast-jev-compaction) · 5,719 stars -- [Eve](https://github.com/vercel/eve) · 5,291 stars -- [Agentgateway · JEV Guardrail](https://github.com/agentgateway/agentgateway) · 4,953 stars -- [Latitude · JEV Preclassifier](https://github.com/latitude-dev/latitude-llm) · 4,665 stars -- [Ax · TypeSafe Client](https://github.com/ax-llm/ax) · 2,934 stars -- [SemIf](https://github.com/TheoLeeCJ/SemIf) · 2,749 stars -- [JEV Trader](https://github.com/jarrodwatts/jev-trader) · 1,672 stars -- [NanoJev](https://github.com/TianyuCodings/NanoJev) · 1,672 stars -- [Kev 0.5B](https://github.com/jaredpalmer/kev) · 1,530 stars -- [TypeSafe Skills](https://github.com/typesafe-ai/skills) · 1,388 stars -- [Agent Desktop · JEV Skill](https://github.com/lahfir/agent-desktop) · 1,378 stars -- [Nimble](https://github.com/bespokelabsai/nimble) · 1,357 stars -- [Vellum Assistant · JEV](https://github.com/vellum-ai/vellum-assistant) · 1,293 stars -- [NewsJack](https://github.com/elvisun/newsjack) · 1,271 stars -- [Jevlike](https://github.com/vinnylarouge/jevlike) · 1,132 stars -- [Celesto](https://github.com/CelestoAI/celesto) · 946 stars -- [Atomic](https://github.com/bastani-inc/atomic) · 809 stars -- [AI CLI](https://github.com/vercel-labs/ai-cli) · 808 stars -- [Awesome JEV by TypeSafe](https://github.com/Anil-matcha/awesome-jev-by-typesafe) · 742 stars -- [TypeSafe Computer Use](https://github.com/awlevin/typesafe-computer-use) · 693 stars -- [Aiavatarkit](https://github.com/uezo/aiavatarkit) · 678 stars -- [Kody](https://github.com/kentcdodds/kody) · 659 stars -- [LocalJev](https://github.com/githubnext/localjev) · 657 stars -- [TipTour macOS](https://github.com/milind-soni/tiptour-macos) · 627 stars -- [Agent](https://github.com/AgentiLoop/Agent) · 618 stars -- [Req LLM](https://github.com/agentjido/req_llm) · 580 stars -- [Omg.dev](https://github.com/BennyKok/omg.dev) · 533 stars -- [Jev CU](https://github.com/Sac-Y/Jev-cu) · 519 stars -- [Splash](https://github.com/incoai/splash) · 506 stars -- [Foreman](https://github.com/thruwire/foreman) · 446 stars -- [Jev Review](https://github.com/devagrawal09/jev-review) · 438 stars -- [Simple JEV](https://github.com/featherless-ai/simple-jev) · 428 stars -- [Vexjoy Agent](https://github.com/notque/vexjoy-agent) · 421 stars -- [Smithers](https://github.com/smithersai/smithers) · 418 stars -- [Awesome TypeSafe](https://github.com/AbdelStark/awesome-typesafe) · 414 stars -- [Jev Experiments](https://github.com/dabit3/jev-experiments) · 352 stars -- [JEV Search](https://github.com/superagents-lab/jev-search) · 352 stars -- [Hermes JEV Skills](https://github.com/kerpopule/hermes-jev-skills) · 335 stars -- [WrongStack](https://github.com/WrongStack/WrongStack) · 329 stars -- [Instructor Php](https://github.com/cognesy/instructor-php) · 327 stars -- [Tax Document Classifier](https://github.com/kyotofin/tax-doc-classifier) · 314 stars -- [TypeSafe Mario](https://github.com/fhshaik/typesafe-mario) · 314 stars -- [Mobile JEV](https://github.com/droidrun/mobile-jev) · 304 stars -- [Awesome JEV (cobanov)](https://github.com/cobanov/awesome-jev) · 292 stars -- [JEV Browser Use](https://github.com/wy-coliney/jev-browser-use) · 291 stars -- [JEV Router](https://github.com/gargpratyush/jev-router) · 283 stars -- [Orchestkit](https://github.com/yonatangross/orchestkit) · 280 stars -- [Third Hand](https://github.com/shhivv/third-hand) · 270 stars -- [Awesome JEV Projects](https://github.com/logicrw/awesome-jev-projects) · 264 stars -- [Pg JEV](https://github.com/realZachi/pg-jev) · 259 stars -- [jev-align](https://github.com/sutro-sh/jev-align) · 253 stars -- [Openai Scala Client](https://github.com/cequence-io/openai-scala-client) · 248 stars -- [Openjev](https://github.com/razorback16/openjev) · 245 stars -- [OpenJEV SGLang](https://github.com/ekzhang/openjev-sglang) · 245 stars -- [Pi Fabric](https://github.com/monotykamary/pi-fabric) · 241 stars -- [OpenJEV Verdict 2.0](https://github.com/Heman10x-NGU/openJev-verdict-2.0) · 221 stars -- [Skillbox](https://github.com/kitze/skillbox) · 220 stars -- [System One Adapter (Python)](https://github.com/typesafe-ai/system-one-adapter-python) · 218 stars -- [JEV Browser](https://github.com/jkudish/jev-browser) · 209 stars -- [Abide](https://github.com/coldteadotai/abide) · 199 stars -- [Notra](https://github.com/usenotra/notra) · 199 stars -- [TypeSafe SDK Js](https://github.com/typesafe-ai/typesafe-sdk-js) · 196 stars -- [JEV MCP](https://github.com/jkudish/jev-mcp) · 196 stars -- [JEV Visual](https://github.com/hr98w/jev-visual) · 192 stars -- [JEV Review](https://github.com/NiazMorshed2007/jev-review) · 191 stars -- [OpenWhisper](https://github.com/Knuckles92/OpenWhisper) · 187 stars -- [JEV Voice Browser](https://github.com/moritzkremb/jev-voice-browser) · 187 stars -- [Awesome JEV (fatwang2)](https://github.com/fatwang2/awesome-jev) · 185 stars -- [Jeff](https://github.com/logan-markewich/jeff) · 183 stars -- [Decider](https://github.com/Mapika/decider) · 180 stars -- [Interlinked CLI](https://github.com/QuentinCody/interlinked-cli) · 178 stars -- [TypeSafe MCP](https://github.com/itsmostafa/typesafe-mcp) · 173 stars -- [TypeSafe SDK Python](https://github.com/typesafe-ai/typesafe-sdk-python) · 171 stars -- [Perch](https://github.com/lakeday-org/perch) · 167 stars -- [Runline](https://github.com/Michaelliv/runline) · 162 stars -- [Compact Adviser](https://github.com/kunchenguid/compact-adviser) · 157 stars -- [Unclutter](https://github.com/kitze/unclutter) · 152 stars -- [djev-spark](https://github.com/mmastrac/djev-spark) · 152 stars -- [Jevpilot](https://github.com/standardagents/jevpilot) · 143 stars -- [AI](https://github.com/hackclub/ai) · 133 stars -- [Pi JEV](https://github.com/y0usaf/pi-jev) · 131 stars -- [JEV Pruner](https://github.com/tamaratran/jev-pruner) · 130 stars -- [Building with JEV Skill](https://github.com/dbreunig/building-with-jev-skill) · 128 stars -- [JEV Codex Router](https://github.com/0xNatoshi/jev-codex-router) · 125 stars -- [jev-semgrep](https://github.com/uehaj/jev-semgrep) · 122 stars -- [Effect Agent](https://github.com/danieljvdm/effect-agent) · 121 stars -- [Pi Warden](https://github.com/DevMortimer/pi-warden) · 118 stars -- [Taskuary](https://github.com/ldbumble/taskuary) · 116 stars -- [JEV Eval Agent](https://github.com/vinilana/jev-eval-agent) · 99 stars -- [JEV Drone](https://github.com/RomanSlack/jev-drone) · 96 stars -- [Bluenoise](https://github.com/rokcso/bluenoise) · 90 stars -- [Advocaat](https://github.com/pithings/advocaat) · 88 stars -- [Youtube Sponsor Detection](https://github.com/trungdq88/youtube-sponsor-detection) · 81 stars -- [Pg TypeSafe](https://github.com/giuliosmall/pg_typesafe) · 81 stars -- [JEV Shell History](https://github.com/mrnugget/jev-shell-history) · 80 stars -- [jev-gateway](https://github.com/vinilana/jev-gateway) · 79 stars -- [Jevmeter](https://github.com/ChetasLua/jevmeter) · 77 stars -- [Captaincore](https://github.com/CaptainCore/captaincore) · 71 stars -- [TypeSafe Adblock](https://github.com/realZachi/typesafe-adblock) · 64 stars -- [jegrep](https://github.com/can1357/jegrep) · 57 stars -- [Hono Jev Router](https://github.com/yusukebe/hono-jev-router) · 45 stars -- [Live Jev](https://github.com/okinaaudio/live-jev) · 38 stars -- [Jev Reviewer](https://github.com/choxos/jev-reviewer) · 30 stars -- [JEV Commit](https://github.com/valentynkit/jev-commit) · 8 stars -- [JEV Skip](https://github.com/valentynkit/jev-skip) · 3 stars -- [Jev.nvim](https://github.com/valentynkit/jev.nvim) · 3 stars + +## 全 147 プロジェクト + +- [LangChain · TypeSafe](https://github.com/langchain-ai/langchain) · 146,779 Star +- [AI Hedge Fund · JEV Adapter](https://github.com/virattt/ai-hedge-fund) · 63,642 Star +- [LiteLLM · JEV Router](https://github.com/BerriAI/litellm) · 59,305 Star +- [Oh My Pi · JEV Judgments](https://github.com/can1357/oh-my-pi) · 32,236 Star +- [Jev Model Router](https://github.com/davila7/claude-code-templates) · 30,870 Star +- [Composio · TypeSafe Provider](https://github.com/ComposioHQ/composio) · 30,268 Star +- [Vercel AI SDK · TypeSafe](https://github.com/vercel/ai) · 26,870 Star +- [Cua · JEV Use](https://github.com/trycua/cua) · 25,422 Star +- [Openwork](https://github.com/different-ai/openwork) · 23,682 Star +- [Pydantic AI · TypeSafe](https://github.com/pydantic/pydantic-ai) · 20,084 Star +- [Eliza · TypeSafe Client](https://github.com/elizaOS/eliza) · 19,404 Star +- [LangChain.js · TypeSafe](https://github.com/langchain-ai/langchainjs) · 18,215 Star +- [json-render · JEV Compose](https://github.com/vercel-labs/json-render) · 17,731 Star +- [Jev Ultrafast](https://github.com/browser-use/jev-ultrafast) · 13,811 Star +- [QuantDinger · JEV Gate](https://github.com/OpenByteInc/QuantDinger) · 11,883 Star +- [OpenChamber · JEV Router](https://github.com/openchamber/openchamber) · 10,213 Star +- [Rig · TypeSafe Crate](https://github.com/0xPlaygrounds/rig) · 8,691 Star +- [Firstmate · JEV Dispatch](https://github.com/kunchenguid/firstmate) · 6,889 Star +- [Laya](https://github.com/NandhaKishorM/laya) · 6,688 Star +- [Fast Jev Compaction](https://github.com/tamaratran/fast-jev-compaction) · 5,719 Star +- [Eve](https://github.com/vercel/eve) · 5,291 Star +- [Agentgateway · JEV Guardrail](https://github.com/agentgateway/agentgateway) · 4,953 Star +- [Latitude · JEV Preclassifier](https://github.com/latitude-dev/latitude-llm) · 4,665 Star +- [Ax · TypeSafe Client](https://github.com/ax-llm/ax) · 2,934 Star +- [SemIf](https://github.com/TheoLeeCJ/SemIf) · 2,749 Star +- [JEV Trader](https://github.com/jarrodwatts/jev-trader) · 1,672 Star +- [NanoJev](https://github.com/TianyuCodings/NanoJev) · 1,672 Star +- [Kev 0.5B](https://github.com/jaredpalmer/kev) · 1,530 Star +- [TypeSafe Skills](https://github.com/typesafe-ai/skills) · 1,388 Star +- [Agent Desktop · JEV Skill](https://github.com/lahfir/agent-desktop) · 1,378 Star +- [Nimble](https://github.com/bespokelabsai/nimble) · 1,357 Star +- [Vellum Assistant · JEV](https://github.com/vellum-ai/vellum-assistant) · 1,293 Star +- [NewsJack](https://github.com/elvisun/newsjack) · 1,271 Star +- [Jevlike](https://github.com/vinnylarouge/jevlike) · 1,132 Star +- [Celesto](https://github.com/CelestoAI/celesto) · 946 Star +- [Atomic](https://github.com/bastani-inc/atomic) · 809 Star +- [AI CLI](https://github.com/vercel-labs/ai-cli) · 808 Star +- [Awesome JEV (yibie)](https://github.com/yibie/awesome-jev) · 805 Star +- [Awesome JEV by TypeSafe](https://github.com/Anil-matcha/awesome-jev-by-typesafe) · 742 Star +- [TypeSafe Computer Use](https://github.com/awlevin/typesafe-computer-use) · 693 Star +- [Aiavatarkit](https://github.com/uezo/aiavatarkit) · 678 Star +- [Kody](https://github.com/kentcdodds/kody) · 659 Star +- [LocalJev](https://github.com/githubnext/localjev) · 657 Star +- [TipTour macOS](https://github.com/milind-soni/tiptour-macos) · 627 Star +- [Agent](https://github.com/AgentiLoop/Agent) · 618 Star +- [Awesome JEV Tools](https://github.com/v-modal/awesome-jev-tools) · 599 Star +- [Req LLM](https://github.com/agentjido/req_llm) · 580 Star +- [Omg.dev](https://github.com/BennyKok/omg.dev) · 533 Star +- [Jev CU](https://github.com/Sac-Y/Jev-cu) · 519 Star +- [Splash](https://github.com/incoai/splash) · 506 Star +- [Foreman](https://github.com/thruwire/foreman) · 446 Star +- [Jev Review](https://github.com/devagrawal09/jev-review) · 438 Star +- [Simple JEV](https://github.com/featherless-ai/simple-jev) · 428 Star +- [Vexjoy Agent](https://github.com/notque/vexjoy-agent) · 421 Star +- [Smithers](https://github.com/smithersai/smithers) · 418 Star +- [Awesome TypeSafe](https://github.com/AbdelStark/awesome-typesafe) · 414 Star +- [Classifier.dev](https://github.com/mrmps/classifier-dev) · 396 Star +- [Astra + JEV Minecraft Agent](https://github.com/rmalde/minecraft-agent) · 395 Star +- [Jev Experiments](https://github.com/dabit3/jev-experiments) · 352 Star +- [JEV Search](https://github.com/superagents-lab/jev-search) · 352 Star +- [Hermes JEV Skills](https://github.com/kerpopule/hermes-jev-skills) · 335 Star +- [WrongStack](https://github.com/WrongStack/WrongStack) · 329 Star +- [Instructor Php](https://github.com/cognesy/instructor-php) · 327 Star +- [Tax Document Classifier](https://github.com/kyotofin/tax-doc-classifier) · 314 Star +- [TypeSafe Mario](https://github.com/fhshaik/typesafe-mario) · 314 Star +- [Mobile JEV](https://github.com/droidrun/mobile-jev) · 304 Star +- [Von](https://github.com/wfzyx/von) · 297 Star +- [Awesome JEV (cobanov)](https://github.com/cobanov/awesome-jev) · 292 Star +- [JEV Browser Use](https://github.com/wy-coliney/jev-browser-use) · 291 Star +- [JEV Router](https://github.com/gargpratyush/jev-router) · 283 Star +- [Orchestkit](https://github.com/yonatangross/orchestkit) · 280 Star +- [Third Hand](https://github.com/shhivv/third-hand) · 270 Star +- [Awesome JEV Projects](https://github.com/logicrw/awesome-jev-projects) · 264 Star +- [Pg JEV](https://github.com/realZachi/pg-jev) · 259 Star +- [jev-align](https://github.com/sutro-sh/jev-align) · 253 Star +- [Openai Scala Client](https://github.com/cequence-io/openai-scala-client) · 248 Star +- [Openjev](https://github.com/razorback16/openjev) · 245 Star +- [OpenJEV SGLang](https://github.com/ekzhang/openjev-sglang) · 245 Star +- [Pi Fabric](https://github.com/monotykamary/pi-fabric) · 241 Star +- [OpenJEV Verdict 2.0](https://github.com/Heman10x-NGU/openJev-verdict-2.0) · 221 Star +- [Skillbox](https://github.com/kitze/skillbox) · 220 Star +- [System One Adapter (Python)](https://github.com/typesafe-ai/system-one-adapter-python) · 218 Star +- [JEV Browser](https://github.com/jkudish/jev-browser) · 209 Star +- [Abide](https://github.com/coldteadotai/abide) · 199 Star +- [Notra](https://github.com/usenotra/notra) · 199 Star +- [JEV MCP](https://github.com/jkudish/jev-mcp) · 196 Star +- [TypeSafe SDK Js](https://github.com/typesafe-ai/typesafe-sdk-js) · 196 Star +- [JEV Visual](https://github.com/hr98w/jev-visual) · 192 Star +- [JEV Review](https://github.com/NiazMorshed2007/jev-review) · 191 Star +- [JEV Voice Browser](https://github.com/moritzkremb/jev-voice-browser) · 187 Star +- [OpenWhisper](https://github.com/Knuckles92/OpenWhisper) · 187 Star +- [Awesome JEV (fatwang2)](https://github.com/fatwang2/awesome-jev) · 185 Star +- [Jeff](https://github.com/logan-markewich/jeff) · 183 Star +- [Awesome JEV (AnotiaWang)](https://github.com/AnotiaWang/awesome-jev) · 181 Star +- [Decider](https://github.com/Mapika/decider) · 180 Star +- [Interlinked CLI](https://github.com/QuentinCody/interlinked-cli) · 178 Star +- [TypeSafe MCP](https://github.com/itsmostafa/typesafe-mcp) · 173 Star +- [TypeSafe SDK Python](https://github.com/typesafe-ai/typesafe-sdk-python) · 171 Star +- [Perch](https://github.com/lakeday-org/perch) · 167 Star +- [Runline](https://github.com/Michaelliv/runline) · 162 Star +- [Compact Adviser](https://github.com/kunchenguid/compact-adviser) · 157 Star +- [djev-spark](https://github.com/mmastrac/djev-spark) · 152 Star +- [Unclutter](https://github.com/kitze/unclutter) · 152 Star +- [Jevpilot](https://github.com/standardagents/jevpilot) · 143 Star +- [AI](https://github.com/hackclub/ai) · 133 Star +- [Awesome JEV Gallery](https://github.com/OmniJev/awesome-jev-gallery) · 131 Star +- [Pi JEV](https://github.com/y0usaf/pi-jev) · 131 Star +- [JEV Pruner](https://github.com/tamaratran/jev-pruner) · 130 Star +- [Building with JEV Skill](https://github.com/dbreunig/building-with-jev-skill) · 128 Star +- [JEV Codex Router](https://github.com/0xNatoshi/jev-codex-router) · 125 Star +- [JevRouter](https://github.com/BillionsBobby/JevRouter) · 125 Star +- [jev-semgrep](https://github.com/uehaj/jev-semgrep) · 122 Star +- [Effect Agent](https://github.com/danieljvdm/effect-agent) · 121 Star +- [Pi Warden](https://github.com/DevMortimer/pi-warden) · 118 Star +- [Taskuary](https://github.com/ldbumble/taskuary) · 116 Star +- [Awesome JEV TypeSafe](https://github.com/valentynkit/awesome-jev-typesafe) · 115 Star +- [Awesome Jev](https://github.com/hellogumbo/awesome-jev) · 109 Star +- [Skillranker](https://github.com/Dicklesworthstone/skillranker) · 107 Star +- [Stanley Code](https://github.com/devagrawal09/stanley-code) · 106 Star +- [JEV Eval Agent](https://github.com/vinilana/jev-eval-agent) · 99 Star +- [Formanator](https://github.com/timrogers/formanator) · 98 Star +- [JEV Drone](https://github.com/RomanSlack/jev-drone) · 96 Star +- [Reflex](https://github.com/kshetrajna12/reflex) · 91 Star +- [Bluenoise](https://github.com/rokcso/bluenoise) · 90 Star +- [Dasheng](https://github.com/wquguru/dasheng) · 90 Star +- [Advocaat](https://github.com/pithings/advocaat) · 88 Star +- [Supercov](https://github.com/supercorp-ai/supercov) · 85 Star +- [Open JEV](https://github.com/daseinlabs/open-jev) · 82 Star +- [Pg TypeSafe](https://github.com/giuliosmall/pg_typesafe) · 81 Star +- [Youtube Sponsor Detection](https://github.com/trungdq88/youtube-sponsor-detection) · 81 Star +- [JEV Shell History](https://github.com/mrnugget/jev-shell-history) · 80 Star +- [JEV Use](https://github.com/savka777/jev-use) · 79 Star +- [jev-gateway](https://github.com/vinilana/jev-gateway) · 79 Star +- [Jevmeter](https://github.com/ChetasLua/jevmeter) · 77 Star +- [Captaincore](https://github.com/CaptainCore/captaincore) · 71 Star +- [JEV Chat](https://github.com/w3cj/jev-chat) · 71 Star +- [Grok Bot JEV](https://github.com/Bodila51/grok-bot-jev) · 68 Star +- [JEV Trade](https://github.com/aowang-ai/jev-trade) · 68 Star +- [Awesome JEV (AppitStudio)](https://github.com/AppitStudio/awesome-jev) · 66 Star +- [TypeSafe Adblock](https://github.com/realZachi/typesafe-adblock) · 64 Star +- [JEV Browser](https://github.com/Ying-Kai-Liao/jev-browser) · 62 Star +- [Save Token JEV Clean](https://github.com/IAmUnbounded/save-token-jev-clean) · 62 Star +- [Agent Router](https://github.com/nidhi-singh02/agent-router) · 58 Star +- [jegrep](https://github.com/can1357/jegrep) · 57 Star +- [Neo4JEV](https://github.com/jexp/neo4jev) · 57 Star +- [Prism Liquidity Agent](https://github.com/irfndi/prism-liquidity-agent) · 54 Star +- [Oxlint Plugin JEV](https://github.com/wobsoriano/oxlint-plugin-jev) · 52 Star ## BeatAPI @@ -211,61 +234,3 @@ JEV は BeatAPI で提供中です。同じ BeatAPI キーと USD 残高を使 --- BeatAPI がキュレーション · ライブギャラリー · ライセンスと注記 - - -- [Celesto](https://github.com/CelestoAI/celesto) -- [Atomic](https://github.com/bastani-inc/atomic) -- [Aiavatarkit](https://github.com/uezo/aiavatarkit) -- [Kody](https://github.com/kentcdodds/kody) -- [Agent](https://github.com/AgentiLoop/Agent) -- [Req LLM](https://github.com/agentjido/req_llm) -- [Omg.dev](https://github.com/BennyKok/omg.dev) -- [Vexjoy Agent](https://github.com/notque/vexjoy-agent) -- [Foreman](https://github.com/thruwire/foreman) -- [WrongStack](https://github.com/WrongStack/WrongStack) -- [Instructor Php](https://github.com/cognesy/instructor-php) -- [TypeSafe Computer Use](https://github.com/awlevin/typesafe-computer-use) -- [Jev Review](https://github.com/devagrawal09/jev-review) -- [Orchestkit](https://github.com/yonatangross/orchestkit) -- [TypeSafe Mario](https://github.com/fhshaik/typesafe-mario) -- [Openai Scala Client](https://github.com/cequence-io/openai-scala-client) -- [Pi Fabric](https://github.com/monotykamary/pi-fabric) -- [OpenWhisper](https://github.com/Knuckles92/OpenWhisper) -- [Pg JEV](https://github.com/realZachi/pg-jev) -- [Interlinked CLI](https://github.com/QuentinCody/interlinked-cli) -- [JEV Router](https://github.com/gargpratyush/jev-router) -- [Skillbox](https://github.com/kitze/skillbox) -- [Mobile JEV](https://github.com/droidrun/mobile-jev) -- [Runline](https://github.com/Michaelliv/runline) -- [JEV Search](https://github.com/superagents-lab/jev-search) -- [JEV Browser Use](https://github.com/wy-coliney/jev-browser-use) -- [JEV Review](https://github.com/NiazMorshed2007/jev-review) -- [Effect Agent](https://github.com/danieljvdm/effect-agent) -- [JEV Browser](https://github.com/jkudish/jev-browser) -- [Unclutter](https://github.com/kitze/unclutter) -- [TypeSafe SDK Python](https://github.com/typesafe-ai/typesafe-sdk-python) -- [JEV Eval Agent](https://github.com/vinilana/jev-eval-agent) -- [Bluenoise](https://github.com/rokcso/bluenoise) -- [TypeSafe MCP](https://github.com/itsmostafa/typesafe-mcp) -- [JEV Shell History](https://github.com/mrnugget/jev-shell-history) -- [JEV Codex Router](https://github.com/0xNatoshi/jev-codex-router) -- [TypeSafe Adblock](https://github.com/realZachi/typesafe-adblock) -- [JEV Skip](https://github.com/valentynkit/jev-skip) -- [JEV Commit](https://github.com/valentynkit/jev-commit) -- [Jev.nvim](https://github.com/valentynkit/jev.nvim) -- [Jevpilot](https://github.com/standardagents/jevpilot) -- [JEV Drone](https://github.com/RomanSlack/jev-drone) -- [Youtube Sponsor Detection](https://github.com/trungdq88/youtube-sponsor-detection) -- [Jevmeter](https://github.com/ChetasLua/jevmeter) -- [Captaincore](https://github.com/CaptainCore/captaincore) -- [Pg TypeSafe](https://github.com/giuliosmall/pg_typesafe) -- [Simple JEV](https://github.com/featherless-ai/simple-jev) -- [TypeSafe SDK Js](https://github.com/typesafe-ai/typesafe-sdk-js) -- [AI](https://github.com/hackclub/ai) -- [Taskuary](https://github.com/ldbumble/taskuary) -- [JEV Voice Browser](https://github.com/moritzkremb/jev-voice-browser) -- [JEV MCP](https://github.com/jkudish/jev-mcp) -- [Advocaat](https://github.com/pithings/advocaat) -- [Pi JEV](https://github.com/y0usaf/pi-jev) -- [Pi Warden](https://github.com/DevMortimer/pi-warden) -- [Openjev](https://github.com/razorback16/openjev) diff --git a/README.md b/README.md index a82aaad..a7b0331 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,7 @@

Browse the live Awesome JEV gallery · Featured projects · - All 125 projects · + All 147 projects · JSON catalogue · 简体中文 · 日本語 @@ -13,9 +13,9 @@

Awesome JEV

-

A source-reviewed gallery of JEV-related projects with 100+ GitHub stars — integrations, tools, open models, and experiments.

+

A source-reviewed gallery of JEV-related projects with 50+ GitHub stars — integrations, tools, open models, experiments, and ecosystem resources.

-

We only list projects at or above 100 stars. See where JEV chooses, scores, routes, or filters—while application code keeps control of execution.

+

We list source-reviewed JEV-related repositories at or above 50 stars. See where JEV chooses, scores, routes, or filters—while application code keeps control of execution.

At a glance

@@ -31,7 +31,7 @@ - 125 + 147 34 10 2026-09-21 @@ -43,16 +43,16 @@

Browse by category

- Browser & Computer Use · 3 · - SDK Integrations · 9 · - Routing · 4 · - Open Models · 8 · - Search & Data · 4
- Safety & Review · 5 · - Agent Workflows · 3 · - Interfaces · 3 · - Developer Tools · 2 · - Domain Tools · 3 + Browser & computer use · 14 · + SDK integrations · 23 · + Routing & optimization · 14 · + Open models · 17 · + Search & data · 9
+ Safety & review · 12 · + Agent workflows · 11 · + Interfaces & automation · 8 · + Developer tools · 27 · + Domain tools · 12

## Featured project gallery @@ -72,7 +72,8 @@

Explore with filters and full descriptions →

-## All 125 projects + +## All 147 projects - [LangChain · TypeSafe](https://github.com/langchain-ai/langchain) · 146,779 stars - [AI Hedge Fund · JEV Adapter](https://github.com/virattt/ai-hedge-fund) · 63,642 stars @@ -111,6 +112,7 @@ - [Celesto](https://github.com/CelestoAI/celesto) · 946 stars - [Atomic](https://github.com/bastani-inc/atomic) · 809 stars - [AI CLI](https://github.com/vercel-labs/ai-cli) · 808 stars +- [Awesome JEV (yibie)](https://github.com/yibie/awesome-jev) · 805 stars - [Awesome JEV by TypeSafe](https://github.com/Anil-matcha/awesome-jev-by-typesafe) · 742 stars - [TypeSafe Computer Use](https://github.com/awlevin/typesafe-computer-use) · 693 stars - [Aiavatarkit](https://github.com/uezo/aiavatarkit) · 678 stars @@ -118,6 +120,7 @@ - [LocalJev](https://github.com/githubnext/localjev) · 657 stars - [TipTour macOS](https://github.com/milind-soni/tiptour-macos) · 627 stars - [Agent](https://github.com/AgentiLoop/Agent) · 618 stars +- [Awesome JEV Tools](https://github.com/v-modal/awesome-jev-tools) · 599 stars - [Req LLM](https://github.com/agentjido/req_llm) · 580 stars - [Omg.dev](https://github.com/BennyKok/omg.dev) · 533 stars - [Jev CU](https://github.com/Sac-Y/Jev-cu) · 519 stars @@ -128,6 +131,8 @@ - [Vexjoy Agent](https://github.com/notque/vexjoy-agent) · 421 stars - [Smithers](https://github.com/smithersai/smithers) · 418 stars - [Awesome TypeSafe](https://github.com/AbdelStark/awesome-typesafe) · 414 stars +- [Classifier.dev](https://github.com/mrmps/classifier-dev) · 396 stars +- [Astra + JEV Minecraft Agent](https://github.com/rmalde/minecraft-agent) · 395 stars - [Jev Experiments](https://github.com/dabit3/jev-experiments) · 352 stars - [JEV Search](https://github.com/superagents-lab/jev-search) · 352 stars - [Hermes JEV Skills](https://github.com/kerpopule/hermes-jev-skills) · 335 stars @@ -136,6 +141,7 @@ - [Tax Document Classifier](https://github.com/kyotofin/tax-doc-classifier) · 314 stars - [TypeSafe Mario](https://github.com/fhshaik/typesafe-mario) · 314 stars - [Mobile JEV](https://github.com/droidrun/mobile-jev) · 304 stars +- [Von](https://github.com/wfzyx/von) · 297 stars - [Awesome JEV (cobanov)](https://github.com/cobanov/awesome-jev) · 292 stars - [JEV Browser Use](https://github.com/wy-coliney/jev-browser-use) · 291 stars - [JEV Router](https://github.com/gargpratyush/jev-router) · 283 stars @@ -154,14 +160,15 @@ - [JEV Browser](https://github.com/jkudish/jev-browser) · 209 stars - [Abide](https://github.com/coldteadotai/abide) · 199 stars - [Notra](https://github.com/usenotra/notra) · 199 stars -- [TypeSafe SDK Js](https://github.com/typesafe-ai/typesafe-sdk-js) · 196 stars - [JEV MCP](https://github.com/jkudish/jev-mcp) · 196 stars +- [TypeSafe SDK Js](https://github.com/typesafe-ai/typesafe-sdk-js) · 196 stars - [JEV Visual](https://github.com/hr98w/jev-visual) · 192 stars - [JEV Review](https://github.com/NiazMorshed2007/jev-review) · 191 stars -- [OpenWhisper](https://github.com/Knuckles92/OpenWhisper) · 187 stars - [JEV Voice Browser](https://github.com/moritzkremb/jev-voice-browser) · 187 stars +- [OpenWhisper](https://github.com/Knuckles92/OpenWhisper) · 187 stars - [Awesome JEV (fatwang2)](https://github.com/fatwang2/awesome-jev) · 185 stars - [Jeff](https://github.com/logan-markewich/jeff) · 183 stars +- [Awesome JEV (AnotiaWang)](https://github.com/AnotiaWang/awesome-jev) · 181 stars - [Decider](https://github.com/Mapika/decider) · 180 stars - [Interlinked CLI](https://github.com/QuentinCody/interlinked-cli) · 178 stars - [TypeSafe MCP](https://github.com/itsmostafa/typesafe-mcp) · 173 stars @@ -169,36 +176,52 @@ - [Perch](https://github.com/lakeday-org/perch) · 167 stars - [Runline](https://github.com/Michaelliv/runline) · 162 stars - [Compact Adviser](https://github.com/kunchenguid/compact-adviser) · 157 stars -- [Unclutter](https://github.com/kitze/unclutter) · 152 stars - [djev-spark](https://github.com/mmastrac/djev-spark) · 152 stars +- [Unclutter](https://github.com/kitze/unclutter) · 152 stars - [Jevpilot](https://github.com/standardagents/jevpilot) · 143 stars - [AI](https://github.com/hackclub/ai) · 133 stars +- [Awesome JEV Gallery](https://github.com/OmniJev/awesome-jev-gallery) · 131 stars - [Pi JEV](https://github.com/y0usaf/pi-jev) · 131 stars - [JEV Pruner](https://github.com/tamaratran/jev-pruner) · 130 stars - [Building with JEV Skill](https://github.com/dbreunig/building-with-jev-skill) · 128 stars - [JEV Codex Router](https://github.com/0xNatoshi/jev-codex-router) · 125 stars +- [JevRouter](https://github.com/BillionsBobby/JevRouter) · 125 stars - [jev-semgrep](https://github.com/uehaj/jev-semgrep) · 122 stars - [Effect Agent](https://github.com/danieljvdm/effect-agent) · 121 stars - [Pi Warden](https://github.com/DevMortimer/pi-warden) · 118 stars - [Taskuary](https://github.com/ldbumble/taskuary) · 116 stars +- [Awesome JEV TypeSafe](https://github.com/valentynkit/awesome-jev-typesafe) · 115 stars +- [Awesome Jev](https://github.com/hellogumbo/awesome-jev) · 109 stars +- [Skillranker](https://github.com/Dicklesworthstone/skillranker) · 107 stars +- [Stanley Code](https://github.com/devagrawal09/stanley-code) · 106 stars - [JEV Eval Agent](https://github.com/vinilana/jev-eval-agent) · 99 stars +- [Formanator](https://github.com/timrogers/formanator) · 98 stars - [JEV Drone](https://github.com/RomanSlack/jev-drone) · 96 stars +- [Reflex](https://github.com/kshetrajna12/reflex) · 91 stars - [Bluenoise](https://github.com/rokcso/bluenoise) · 90 stars +- [Dasheng](https://github.com/wquguru/dasheng) · 90 stars - [Advocaat](https://github.com/pithings/advocaat) · 88 stars -- [Youtube Sponsor Detection](https://github.com/trungdq88/youtube-sponsor-detection) · 81 stars +- [Supercov](https://github.com/supercorp-ai/supercov) · 85 stars +- [Open JEV](https://github.com/daseinlabs/open-jev) · 82 stars - [Pg TypeSafe](https://github.com/giuliosmall/pg_typesafe) · 81 stars +- [Youtube Sponsor Detection](https://github.com/trungdq88/youtube-sponsor-detection) · 81 stars - [JEV Shell History](https://github.com/mrnugget/jev-shell-history) · 80 stars +- [JEV Use](https://github.com/savka777/jev-use) · 79 stars - [jev-gateway](https://github.com/vinilana/jev-gateway) · 79 stars - [Jevmeter](https://github.com/ChetasLua/jevmeter) · 77 stars - [Captaincore](https://github.com/CaptainCore/captaincore) · 71 stars +- [JEV Chat](https://github.com/w3cj/jev-chat) · 71 stars +- [Grok Bot JEV](https://github.com/Bodila51/grok-bot-jev) · 68 stars +- [JEV Trade](https://github.com/aowang-ai/jev-trade) · 68 stars +- [Awesome JEV (AppitStudio)](https://github.com/AppitStudio/awesome-jev) · 66 stars - [TypeSafe Adblock](https://github.com/realZachi/typesafe-adblock) · 64 stars +- [JEV Browser](https://github.com/Ying-Kai-Liao/jev-browser) · 62 stars +- [Save Token JEV Clean](https://github.com/IAmUnbounded/save-token-jev-clean) · 62 stars +- [Agent Router](https://github.com/nidhi-singh02/agent-router) · 58 stars - [jegrep](https://github.com/can1357/jegrep) · 57 stars -- [Hono Jev Router](https://github.com/yusukebe/hono-jev-router) · 45 stars -- [Live Jev](https://github.com/okinaaudio/live-jev) · 38 stars -- [Jev Reviewer](https://github.com/choxos/jev-reviewer) · 30 stars -- [JEV Commit](https://github.com/valentynkit/jev-commit) · 8 stars -- [JEV Skip](https://github.com/valentynkit/jev-skip) · 3 stars -- [Jev.nvim](https://github.com/valentynkit/jev.nvim) · 3 stars +- [Neo4JEV](https://github.com/jexp/neo4jev) · 57 stars +- [Prism Liquidity Agent](https://github.com/irfndi/prism-liquidity-agent) · 54 stars +- [Oxlint Plugin JEV](https://github.com/wobsoriano/oxlint-plugin-jev) · 52 stars ## BeatAPI diff --git a/README.zh-CN.md b/README.zh-CN.md index 54f7262..acb87f1 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -5,7 +5,7 @@

浏览 Awesome JEV 主站 Gallery · 精选项目 · - 全部 125 个项目 · + 全部 147 个项目 · JSON 目录 · English · 日本語 @@ -13,9 +13,9 @@

Awesome JEV

-

只整理 100+ Star、经过源码核对的 JEV 相关项目、集成、工具、开放模型与实验。

+

只整理 50+ Star、经过源码核对的 JEV 相关项目、集成、工具、开放模型、实验与生态资源。

-

收录门槛为 GitHub 100 Star 及以上。看看 JEV 如何完成选择、评分、路由与过滤，同时由应用代码掌控执行。

+

收录门槛为 GitHub 50 Star 及以上。看看 JEV 如何完成选择、评分、路由与过滤，同时由应用代码掌控执行。

当前规模

@@ -31,7 +31,7 @@ - 125 + 147 34 10 2026-09-21 @@ -43,16 +43,16 @@

按分类浏览

- 浏览器与电脑操作 · 3 · - SDK 与框架集成 · 9 · - 路由与优化 · 4 · - 开放模型 · 8 · - 搜索与数据 · 4
- 安全与审查 · 5 · - Agent 工作流 · 3 · - 界面与自动化 · 3 · - 开发者工具 · 2 · - 垂直工具 · 3 + 浏览器与电脑操作 · 14 · + SDK 与框架集成 · 23 · + 路由与优化 · 14 · + 开放模型 · 17 · + 搜索与数据 · 9
+ 安全与审查 · 12 · + Agent 工作流 · 11 · + 界面与自动化 · 8 · + 开发者工具 · 27 · + 垂直工具 · 12

## 精选项目 Gallery @@ -72,7 +72,8 @@

在主站筛选并查看完整项目说明 →

-## 全部 125 个项目 + +## 全部 147 个项目 - [LangChain · TypeSafe](https://github.com/langchain-ai/langchain) · 146,779 Star - [AI Hedge Fund · JEV Adapter](https://github.com/virattt/ai-hedge-fund) · 63,642 Star @@ -111,6 +112,7 @@ - [Celesto](https://github.com/CelestoAI/celesto) · 946 Star - [Atomic](https://github.com/bastani-inc/atomic) · 809 Star - [AI CLI](https://github.com/vercel-labs/ai-cli) · 808 Star +- [Awesome JEV (yibie)](https://github.com/yibie/awesome-jev) · 805 Star - [Awesome JEV by TypeSafe](https://github.com/Anil-matcha/awesome-jev-by-typesafe) · 742 Star - [TypeSafe Computer Use](https://github.com/awlevin/typesafe-computer-use) · 693 Star - [Aiavatarkit](https://github.com/uezo/aiavatarkit) · 678 Star @@ -118,6 +120,7 @@ - [LocalJev](https://github.com/githubnext/localjev) · 657 Star - [TipTour macOS](https://github.com/milind-soni/tiptour-macos) · 627 Star - [Agent](https://github.com/AgentiLoop/Agent) · 618 Star +- [Awesome JEV Tools](https://github.com/v-modal/awesome-jev-tools) · 599 Star - [Req LLM](https://github.com/agentjido/req_llm) · 580 Star - [Omg.dev](https://github.com/BennyKok/omg.dev) · 533 Star - [Jev CU](https://github.com/Sac-Y/Jev-cu) · 519 Star @@ -128,6 +131,8 @@ - [Vexjoy Agent](https://github.com/notque/vexjoy-agent) · 421 Star - [Smithers](https://github.com/smithersai/smithers) · 418 Star - [Awesome TypeSafe](https://github.com/AbdelStark/awesome-typesafe) · 414 Star +- [Classifier.dev](https://github.com/mrmps/classifier-dev) · 396 Star +- [Astra + JEV Minecraft Agent](https://github.com/rmalde/minecraft-agent) · 395 Star - [Jev Experiments](https://github.com/dabit3/jev-experiments) · 352 Star - [JEV Search](https://github.com/superagents-lab/jev-search) · 352 Star - [Hermes JEV Skills](https://github.com/kerpopule/hermes-jev-skills) · 335 Star @@ -136,6 +141,7 @@ - [Tax Document Classifier](https://github.com/kyotofin/tax-doc-classifier) · 314 Star - [TypeSafe Mario](https://github.com/fhshaik/typesafe-mario) · 314 Star - [Mobile JEV](https://github.com/droidrun/mobile-jev) · 304 Star +- [Von](https://github.com/wfzyx/von) · 297 Star - [Awesome JEV (cobanov)](https://github.com/cobanov/awesome-jev) · 292 Star - [JEV Browser Use](https://github.com/wy-coliney/jev-browser-use) · 291 Star - [JEV Router](https://github.com/gargpratyush/jev-router) · 283 Star @@ -154,14 +160,15 @@ - [JEV Browser](https://github.com/jkudish/jev-browser) · 209 Star - [Abide](https://github.com/coldteadotai/abide) · 199 Star - [Notra](https://github.com/usenotra/notra) · 199 Star -- [TypeSafe SDK Js](https://github.com/typesafe-ai/typesafe-sdk-js) · 196 Star - [JEV MCP](https://github.com/jkudish/jev-mcp) · 196 Star +- [TypeSafe SDK Js](https://github.com/typesafe-ai/typesafe-sdk-js) · 196 Star - [JEV Visual](https://github.com/hr98w/jev-visual) · 192 Star - [JEV Review](https://github.com/NiazMorshed2007/jev-review) · 191 Star -- [OpenWhisper](https://github.com/Knuckles92/OpenWhisper) · 187 Star - [JEV Voice Browser](https://github.com/moritzkremb/jev-voice-browser) · 187 Star +- [OpenWhisper](https://github.com/Knuckles92/OpenWhisper) · 187 Star - [Awesome JEV (fatwang2)](https://github.com/fatwang2/awesome-jev) · 185 Star - [Jeff](https://github.com/logan-markewich/jeff) · 183 Star +- [Awesome JEV (AnotiaWang)](https://github.com/AnotiaWang/awesome-jev) · 181 Star - [Decider](https://github.com/Mapika/decider) · 180 Star - [Interlinked CLI](https://github.com/QuentinCody/interlinked-cli) · 178 Star - [TypeSafe MCP](https://github.com/itsmostafa/typesafe-mcp) · 173 Star @@ -169,36 +176,52 @@ - [Perch](https://github.com/lakeday-org/perch) · 167 Star - [Runline](https://github.com/Michaelliv/runline) · 162 Star - [Compact Adviser](https://github.com/kunchenguid/compact-adviser) · 157 Star -- [Unclutter](https://github.com/kitze/unclutter) · 152 Star - [djev-spark](https://github.com/mmastrac/djev-spark) · 152 Star +- [Unclutter](https://github.com/kitze/unclutter) · 152 Star - [Jevpilot](https://github.com/standardagents/jevpilot) · 143 Star - [AI](https://github.com/hackclub/ai) · 133 Star +- [Awesome JEV Gallery](https://github.com/OmniJev/awesome-jev-gallery) · 131 Star - [Pi JEV](https://github.com/y0usaf/pi-jev) · 131 Star - [JEV Pruner](https://github.com/tamaratran/jev-pruner) · 130 Star - [Building with JEV Skill](https://github.com/dbreunig/building-with-jev-skill) · 128 Star - [JEV Codex Router](https://github.com/0xNatoshi/jev-codex-router) · 125 Star +- [JevRouter](https://github.com/BillionsBobby/JevRouter) · 125 Star - [jev-semgrep](https://github.com/uehaj/jev-semgrep) · 122 Star - [Effect Agent](https://github.com/danieljvdm/effect-agent) · 121 Star - [Pi Warden](https://github.com/DevMortimer/pi-warden) · 118 Star - [Taskuary](https://github.com/ldbumble/taskuary) · 116 Star +- [Awesome JEV TypeSafe](https://github.com/valentynkit/awesome-jev-typesafe) · 115 Star +- [Awesome Jev](https://github.com/hellogumbo/awesome-jev) · 109 Star +- [Skillranker](https://github.com/Dicklesworthstone/skillranker) · 107 Star +- [Stanley Code](https://github.com/devagrawal09/stanley-code) · 106 Star - [JEV Eval Agent](https://github.com/vinilana/jev-eval-agent) · 99 Star +- [Formanator](https://github.com/timrogers/formanator) · 98 Star - [JEV Drone](https://github.com/RomanSlack/jev-drone) · 96 Star +- [Reflex](https://github.com/kshetrajna12/reflex) · 91 Star - [Bluenoise](https://github.com/rokcso/bluenoise) · 90 Star +- [Dasheng](https://github.com/wquguru/dasheng) · 90 Star - [Advocaat](https://github.com/pithings/advocaat) · 88 Star -- [Youtube Sponsor Detection](https://github.com/trungdq88/youtube-sponsor-detection) · 81 Star +- [Supercov](https://github.com/supercorp-ai/supercov) · 85 Star +- [Open JEV](https://github.com/daseinlabs/open-jev) · 82 Star - [Pg TypeSafe](https://github.com/giuliosmall/pg_typesafe) · 81 Star +- [Youtube Sponsor Detection](https://github.com/trungdq88/youtube-sponsor-detection) · 81 Star - [JEV Shell History](https://github.com/mrnugget/jev-shell-history) · 80 Star +- [JEV Use](https://github.com/savka777/jev-use) · 79 Star - [jev-gateway](https://github.com/vinilana/jev-gateway) · 79 Star - [Jevmeter](https://github.com/ChetasLua/jevmeter) · 77 Star - [Captaincore](https://github.com/CaptainCore/captaincore) · 71 Star +- [JEV Chat](https://github.com/w3cj/jev-chat) · 71 Star +- [Grok Bot JEV](https://github.com/Bodila51/grok-bot-jev) · 68 Star +- [JEV Trade](https://github.com/aowang-ai/jev-trade) · 68 Star +- [Awesome JEV (AppitStudio)](https://github.com/AppitStudio/awesome-jev) · 66 Star - [TypeSafe Adblock](https://github.com/realZachi/typesafe-adblock) · 64 Star +- [JEV Browser](https://github.com/Ying-Kai-Liao/jev-browser) · 62 Star +- [Save Token JEV Clean](https://github.com/IAmUnbounded/save-token-jev-clean) · 62 Star +- [Agent Router](https://github.com/nidhi-singh02/agent-router) · 58 Star - [jegrep](https://github.com/can1357/jegrep) · 57 Star -- [Hono Jev Router](https://github.com/yusukebe/hono-jev-router) · 45 Star -- [Live Jev](https://github.com/okinaaudio/live-jev) · 38 Star -- [Jev Reviewer](https://github.com/choxos/jev-reviewer) · 30 Star -- [JEV Commit](https://github.com/valentynkit/jev-commit) · 8 Star -- [JEV Skip](https://github.com/valentynkit/jev-skip) · 3 Star -- [Jev.nvim](https://github.com/valentynkit/jev.nvim) · 3 Star +- [Neo4JEV](https://github.com/jexp/neo4jev) · 57 Star +- [Prism Liquidity Agent](https://github.com/irfndi/prism-liquidity-agent) · 54 Star +- [Oxlint Plugin JEV](https://github.com/wobsoriano/oxlint-plugin-jev) · 52 Star ## BeatAPI diff --git a/data/projects.json b/data/projects.json index a9fd5cd..e7d8800 100644 --- a/data/projects.json +++ b/data/projects.json @@ -3,40 +3,10 @@ "capturedAt": "2026-09-21", "source": { "name": "BeatAPI Awesome JEV curation", - "batch": "2026-09-20-github-and-x-refresh", - "policy": "Project-level deduplication. Direct JEV GitHub matches at or above 1,000 stars are included after fixed-source review; lower-star projects may be included for distinctive practical value. X and GitHub are discovery signals, not runtime verification." + "batch": "2026-09-21-star50-two-source-and-code-search", + "policy": "Project-level deduplication. Public JEV-related GitHub repositories at or above 50 stars are included only after fixed-commit source review. Discovery includes awesomejev.com, logicrw/awesome-jev-projects, GitHub repository search, and GitHub code search. Runtime behavior is not independently verified." }, "projects": [ - { - "id": "jev-ultrafast", - "name": "Jev Ultrafast", - "owner": "browser-use", - "category": "browser-computer-use", - "repoUrl": "https://github.com/browser-use/jev-ultrafast", - "evidenceUrl": "https://github.com/browser-use/jev-ultrafast/blob/1231850a0bf1a0c0341fe408ef1668dbbfdfac46/jev_ultrafast/model.py", - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/gregpr07/status/2100411066966749359", - "author": "@gregpr07", - "views": 2948266 - }, - "language": "Python", - "license": "MIT", - "starsAtCapture": 13811, - "summary": { - "en": "A browser agent that uses JEV to choose an action and matching DOM element, calling a text model only when input text is needed.", - "zh": "用 JEV 一次选出浏览器动作与对应 DOM 元素，只在需要输入文本时再调用文本模型。", - "ja": "JEV を使用してアクションと一致する DOM 要素を選択し、入力テキストが必要な場合にのみテキスト モデルを呼び出すブラウザ エージェント。" - }, - "decision": { - "en": "Chooses the next browser action and target element from the current page state.", - "zh": "根据当前页面状态选择下一步浏览器动作和目标元素。", - "ja": "現在のページ状態から次のブラウザ アクションとターゲット要素を選択します。" - }, - "verification": "source-reviewed", - "runtimeVerified": false - }, { "id": "langchain-jev", "name": "LangChain · TypeSafe", @@ -263,6 +233,34 @@ "verification": "source-reviewed", "runtimeVerified": false }, + { + "id": "openwork", + "name": "Openwork", + "owner": "different-ai", + "category": "agent-workflows", + "repoUrl": "https://github.com/different-ai/openwork", + "evidenceUrl": "https://github.com/different-ai/openwork/blob/80c74d2160034fa1738fc6be78dd24ddfeccfc59/.github/scripts/jev-test-coverage-review.mjs", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/different-ai/openwork/blob/80c74d2160034fa1738fc6be78dd24ddfeccfc59/.github/scripts/jev-test-coverage-review.mjs" + }, + "language": "TypeScript", + "license": "Not declared", + "starsAtCapture": 23682, + "summary": { + "en": "An open-source cowork-style agent workspace that can run JEV-backed reviews inside CI and skill workflows.", + "zh": "开源的 cowork 风格 Agent 工作区，可在 CI 与 Skill 流程里跑 JEV 驱动的审查。", + "ja": "CI と Skill ワークフローで JEV レビューを実行できる、オープンソースの cowork 風エージェント作業空間。" + }, + "decision": { + "en": "Scores or gates test-coverage and review findings before merging agent-produced changes.", + "zh": "在合并 Agent 产出前，对测试覆盖与审查结论做评分或门禁。", + "ja": "エージェント成果をマージする前に、テストカバレッジやレビュー結果を評価・ゲートします。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, { "id": "pydantic-ai-typesafe", "name": "Pydantic AI · TypeSafe", @@ -375,6 +373,36 @@ "verification": "source-reviewed", "runtimeVerified": false }, + { + "id": "jev-ultrafast", + "name": "Jev Ultrafast", + "owner": "browser-use", + "category": "browser-computer-use", + "repoUrl": "https://github.com/browser-use/jev-ultrafast", + "evidenceUrl": "https://github.com/browser-use/jev-ultrafast/blob/1231850a0bf1a0c0341fe408ef1668dbbfdfac46/jev_ultrafast/model.py", + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/gregpr07/status/2100411066966749359", + "author": "@gregpr07", + "views": 2948266 + }, + "language": "Python", + "license": "MIT", + "starsAtCapture": 13811, + "summary": { + "en": "A browser agent that uses JEV to choose an action and matching DOM element, calling a text model only when input text is needed.", + "zh": "用 JEV 一次选出浏览器动作与对应 DOM 元素，只在需要输入文本时再调用文本模型。", + "ja": "JEV を使用してアクションと一致する DOM 要素を選択し、入力テキストが必要な場合にのみテキスト モデルを呼び出すブラウザ エージェント。" + }, + "decision": { + "en": "Chooses the next browser action and target element from the current page state.", + "zh": "根据当前页面状态选择下一步浏览器动作和目标元素。", + "ja": "現在のページ状態から次のブラウザ アクションとターゲット要素を選択します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, { "id": "quantdinger-jev", "name": "QuantDinger · JEV Gate", @@ -487,6 +515,93 @@ "verification": "source-reviewed", "runtimeVerified": false }, + { + "id": "laya", + "name": "Laya", + "owner": "NandhaKishorM", + "category": "open-models", + "repoUrl": "https://github.com/NandhaKishorM/laya", + "evidenceUrl": "https://github.com/NandhaKishorM/laya/blob/d113dca2512fb3eaca313534bc54c7162d87c1d4/README.md", + "modelUrl": "https://huggingface.co/convaiinnovations/laya", + "language": "Python", + "license": "Apache-2.0", + "starsAtCapture": 6688, + "summary": { + "en": "Multilingual non-autoregressive System 1 decision engine: typed choice/score/noul in one forward pass, with a router across checkpoints.", + "zh": "多语言非自回归 System 1 决策引擎：单次前向完成类型化 choice/score/noul，并由路由在检查点间选型。", + "ja": "多言語・非自己回帰の System 1 意思決定エンジン。1 回の前向き計算で型付き choice/score/noul を出し、ルータがチェックポイントを選びます。" + }, + "decision": { + "en": "Answers typed questions over text or structured state without generating free-form text to parse.", + "zh": "对文本或结构化状态回答类型化问题，不生成再解析自由文本。", + "ja": "テキストや構造化状態に対する型付き質問に答え、自由文を生成してパースしません。" + }, + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/NandhaKishorM/laya/blob/d113dca2512fb3eaca313534bc54c7162d87c1d4/README.md" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "fast-jev-compaction", + "name": "Fast Jev Compaction", + "owner": "tamaratran", + "category": "developer-tools", + "repoUrl": "https://github.com/tamaratran/fast-jev-compaction", + "evidenceUrl": "https://github.com/tamaratran/fast-jev-compaction/blob/e3f262a7f4d42bd8dd32ced30d26176f7cb545b0/src/client.ts", + "language": "TypeScript", + "license": "MIT", + "starsAtCapture": 5719, + "summary": { + "en": "Compacts Claude Code tool history while keeping retained text verbatim.", + "zh": "压缩 Claude Code 工具历史，同时原样保留仍有价值的内容。", + "ja": "保持されたテキストをそのまま保持しながら、Claude Code ツール履歴を圧縮します。" + }, + "decision": { + "en": "Scores which calls remain useful; local code keeps, truncates, or drops them.", + "zh": "判断哪些调用仍有用，再由本地代码保留、截断或删除。", + "ja": "コールするスコアは依然として有用です。ローカル コードはそれらを保持、切り捨て、または削除します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/tamarajtran/status/2101070206881972243", + "author": "@tamarajtran", + "views": 18175 + } + }, + { + "id": "vercel-eve", + "name": "Eve", + "owner": "vercel", + "category": "agent-workflows", + "repoUrl": "https://github.com/vercel/eve", + "evidenceUrl": "https://github.com/vercel/eve/blob/d004e6d47e9d25d0380c24b5a47b65a18f8b2784/README.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/vercel/eve/blob/d004e6d47e9d25d0380c24b5a47b65a18f8b2784/README.md" + }, + "language": "TypeScript", + "license": "Apache-2.0", + "starsAtCapture": 5291, + "summary": { + "en": "Vercel’s open agent framework for packaging skills, evals, and tool-using workflows.", + "zh": "Vercel 开源的 Agent 框架，用于打包 Skill、评测与带工具的工作流。", + "ja": "Skill・評価・ツール付きワークフローをまとめる Vercel のオープンなエージェント枠組み。" + }, + "decision": { + "en": "Structures agent runs so later steps can apply typed judgments before acting.", + "zh": "把 Agent 运行结构化，便于后续步骤在行动前做类型化判断。", + "ja": "エージェント実行を構造化し、行動前に型付き判断を差し込めるようにします。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, { "id": "agentgateway-jev-guardrail", "name": "Agentgateway · JEV Guardrail", @@ -543,36 +658,6 @@ "verification": "source-reviewed", "runtimeVerified": false }, - { - "id": "fast-jev-compaction", - "name": "Fast Jev Compaction", - "owner": "tamaratran", - "category": "developer-tools", - "repoUrl": "https://github.com/tamaratran/fast-jev-compaction", - "evidenceUrl": "https://github.com/tamaratran/fast-jev-compaction/blob/e3f262a7f4d42bd8dd32ced30d26176f7cb545b0/src/client.ts", - "language": "TypeScript", - "license": "MIT", - "starsAtCapture": 5719, - "summary": { - "en": "Compacts Claude Code tool history while keeping retained text verbatim.", - "zh": "压缩 Claude Code 工具历史，同时原样保留仍有价值的内容。", - "ja": "保持されたテキストをそのまま保持しながら、Claude Code ツール履歴を圧縮します。" - }, - "decision": { - "en": "Scores which calls remain useful; local code keeps, truncates, or drops them.", - "zh": "判断哪些调用仍有用，再由本地代码保留、截断或删除。", - "ja": "コールするスコアは依然として有用です。ローカル コードはそれらを保持、切り捨て、または削除します。" - }, - "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/tamarajtran/status/2101070206881972243", - "author": "@tamarajtran", - "views": 18175 - } - }, { "id": "ax-typesafe", "name": "Ax · TypeSafe Client", @@ -630,35 +715,6 @@ "verification": "source-reviewed", "runtimeVerified": false }, - { - "id": "laya", - "name": "Laya", - "owner": "NandhaKishorM", - "category": "open-models", - "repoUrl": "https://github.com/NandhaKishorM/laya", - "evidenceUrl": "https://github.com/NandhaKishorM/laya/blob/d113dca2512fb3eaca313534bc54c7162d87c1d4/README.md", - "modelUrl": "https://huggingface.co/convaiinnovations/laya", - "language": "Python", - "license": "Apache-2.0", - "starsAtCapture": 6688, - "summary": { - "en": "Multilingual non-autoregressive System 1 decision engine: typed choice/score/noul in one forward pass, with a router across checkpoints.", - "zh": "多语言非自回归 System 1 决策引擎：单次前向完成类型化 choice/score/noul，并由路由在检查点间选型。", - "ja": "多言語・非自己回帰の System 1 意思決定エンジン。1 回の前向き計算で型付き choice/score/noul を出し、ルータがチェックポイントを選びます。" - }, - "decision": { - "en": "Answers typed questions over text or structured state without generating free-form text to parse.", - "zh": "对文本或结构化状态回答类型化问题，不生成再解析自由文本。", - "ja": "テキストや構造化状態に対する型付き質問に答え、自由文を生成してパースしません。" - }, - "source": { - "type": "github", - "label": "GitHub source", - "url": "https://github.com/NandhaKishorM/laya/blob/d113dca2512fb3eaca313534bc54c7162d87c1d4/README.md" - }, - "verification": "source-reviewed", - "runtimeVerified": false - }, { "id": "jev-trader", "name": "JEV Trader", @@ -688,19 +744,106 @@ "runtimeVerified": false }, { - "id": "agent-desktop-jev", - "name": "Agent Desktop · JEV Skill", - "owner": "lahfir", - "category": "browser-computer-use", - "repoUrl": "https://github.com/lahfir/agent-desktop", - "evidenceUrl": "https://github.com/lahfir/agent-desktop/blob/7a8e4a10281c7319733aa200fd79501f34529716/scripts/jev/act.mjs", - "language": "JavaScript", - "license": "Apache-2.0", - "starsAtCapture": 1378, + "id": "nanojev", + "name": "NanoJev", + "owner": "TianyuCodings", + "category": "open-models", + "repoUrl": "https://github.com/TianyuCodings/NanoJev", + "evidenceUrl": "https://github.com/TianyuCodings/NanoJev/blob/71a513bb0163b5634467842b523ee0c0ed6fb1c7/README.md", + "modelUrl": "https://huggingface.co/C-Tianyu/NanoJev", + "language": "Python", + "license": "MIT", + "starsAtCapture": 1672, "summary": { - "en": "An optional JEV skill that chooses native desktop controls and actions from accessibility data.", - "zh": "根据系统无障碍数据选择原生桌面控件与动作的可选 JEV Skill。", - "ja": "アクセシビリティ データからネイティブ デスクトップ コントロールとアクションを選択するオプションの JEV スキル。" + "en": "A 0.6B open replica of the JEV interface with parallel decisions and a training pipeline.", + "zh": "提供并行判断、动态候选与完整训练流程的 0.6B 开放 JEV 接口复刻。", + "ja": "並列決定とトレーニング パイプラインを備えた JEV インターフェイスの 0.6B オープン レプリカ。" + }, + "decision": { + "en": "Scores runtime-defined candidates in one pass and exposes complete probability distributions.", + "zh": "一次前向过程给运行时动态候选评分，并输出完整概率分布。", + "ja": "ランタイム定義の候補を 1 回のパスでスコアリングし、完全な確率分布を明らかにします。" + }, + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/TianyuCodings/NanoJev/blob/71a513bb0163b5634467842b523ee0c0ed6fb1c7/README.md" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "kev", + "name": "Kev 0.5B", + "owner": "jaredpalmer", + "category": "open-models", + "repoUrl": "https://github.com/jaredpalmer/kev", + "evidenceUrl": "https://github.com/jaredpalmer/kev/blob/20fa6268c8ceb226530be2fb5266ab2c36b37724/README.md", + "language": "Python", + "license": "Apache-2.0", + "starsAtCapture": 1530, + "summary": { + "en": "A tiny trainable Jev-like decision model based on Qwen2.5-0.5B.", + "zh": "基于 Qwen2.5-0.5B、可在 MacBook 上训练运行的轻量决策模型。", + "ja": "Qwen2.5-0.5B に基づく、小さなトレーニング可能な JEV のような意思決定モデル。" + }, + "decision": { + "en": "Exposes a TypeSafe-compatible API for bounded local choices and scores.", + "zh": "通过 TypeSafe 兼容接口完成有边界的本地选择与评分。", + "ja": "制限されたローカルの選択肢とスコア用の TypeSafe 互換 API を公開します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/jaredpalmer/status/2101028325472841920", + "author": "@jaredpalmer", + "views": 165852 + } + }, + { + "id": "typesafe-skills", + "name": "TypeSafe Skills", + "owner": "typesafe-ai", + "category": "developer-tools", + "repoUrl": "https://github.com/typesafe-ai/skills", + "evidenceUrl": "https://github.com/typesafe-ai/skills/blob/65a39f393687675ce170e6094757de20370365b9/skills/typesafe-ai/SKILL.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/typesafe-ai/skills/blob/65a39f393687675ce170e6094757de20370365b9/skills/typesafe-ai/SKILL.md" + }, + "language": "Not declared", + "license": "MIT", + "starsAtCapture": 1388, + "summary": { + "en": "Official agent skills for building against TypeSafe’s System One / JEV API.", + "zh": "面向 TypeSafe System One / JEV API 的官方 Agent Skill 集合。", + "ja": "TypeSafe の System One / JEV API 向け公式 Agent Skill 集。" + }, + "decision": { + "en": "Guides agents to frame Noul, Choice, and Score questions against System One.", + "zh": "指导 Agent 把 Noul / Choice / Score 问题正确提交给 System One。", + "ja": "エージェントが Noul / Choice / Score を System One に正しく投げるよう導きます。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "agent-desktop-jev", + "name": "Agent Desktop · JEV Skill", + "owner": "lahfir", + "category": "browser-computer-use", + "repoUrl": "https://github.com/lahfir/agent-desktop", + "evidenceUrl": "https://github.com/lahfir/agent-desktop/blob/7a8e4a10281c7319733aa200fd79501f34529716/scripts/jev/act.mjs", + "language": "JavaScript", + "license": "Apache-2.0", + "starsAtCapture": 1378, + "summary": { + "en": "An optional JEV skill that chooses native desktop controls and actions from accessibility data.", + "zh": "根据系统无障碍数据选择原生桌面控件与动作的可选 JEV Skill。", + "ja": "アクセシビリティ データからネイティブ デスクトップ コントロールとアクションを選択するオプションの JEV スキル。" }, "decision": { "en": "Selects a target and action and estimates presence and risk before local policy executes.", @@ -715,6 +858,36 @@ "verification": "source-reviewed", "runtimeVerified": false }, + { + "id": "nimble", + "name": "Nimble", + "owner": "bespokelabsai", + "category": "open-models", + "repoUrl": "https://github.com/bespokelabsai/nimble", + "evidenceUrl": "https://github.com/bespokelabsai/nimble/blob/35fe1f4fdbc64fa3dbbf5ac0042f3f5680c1ad28/README.md", + "language": "Python", + "license": "Not declared", + "starsAtCapture": 1357, + "summary": { + "en": "An open toolkit for local typed decisions, data curation, and evaluation.", + "zh": "面向本地类型化决策、数据整理与评测的开放工具包。", + "ja": "ローカルでの型付き意思決定、データキュレーション、評価に使えるオープンツールキット。" + }, + "decision": { + "en": "Explores open local classifiers for bounded judgments and comparable evaluations.", + "zh": "探索用于有限判断的开放本地分类器与可比较评测。", + "ja": "境界の明確な判断と比較可能な評価に使える、オープンなローカル分類器を検証します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/aisearchio/status/2101394114176806966", + "author": "@aisearchio", + "views": 63276 + } + }, { "id": "vellum-assistant-jev", "name": "Vellum Assistant · JEV", @@ -773,35 +946,6 @@ "views": 583285 } }, - { - "id": "nanojev", - "name": "NanoJev", - "owner": "TianyuCodings", - "category": "open-models", - "repoUrl": "https://github.com/TianyuCodings/NanoJev", - "evidenceUrl": "https://github.com/TianyuCodings/NanoJev/blob/71a513bb0163b5634467842b523ee0c0ed6fb1c7/README.md", - "modelUrl": "https://huggingface.co/C-Tianyu/NanoJev", - "language": "Python", - "license": "MIT", - "starsAtCapture": 1672, - "summary": { - "en": "A 0.6B open replica of the JEV interface with parallel decisions and a training pipeline.", - "zh": "提供并行判断、动态候选与完整训练流程的 0.6B 开放 JEV 接口复刻。", - "ja": "並列決定とトレーニング パイプラインを備えた JEV インターフェイスの 0.6B オープン レプリカ。" - }, - "decision": { - "en": "Scores runtime-defined candidates in one pass and exposes complete probability distributions.", - "zh": "一次前向过程给运行时动态候选评分，并输出完整概率分布。", - "ja": "ランタイム定義の候補を 1 回のパスでスコアリングし、完全な確率分布を明らかにします。" - }, - "source": { - "type": "github", - "label": "GitHub source", - "url": "https://github.com/TianyuCodings/NanoJev/blob/71a513bb0163b5634467842b523ee0c0ed6fb1c7/README.md" - }, - "verification": "source-reviewed", - "runtimeVerified": false - }, { "id": "jevlike", "name": "Jevlike", @@ -831,94 +975,228 @@ "runtimeVerified": false }, { - "id": "tiptour-macos", - "name": "TipTour macOS", - "owner": "milind-soni", - "category": "interfaces", - "repoUrl": "https://github.com/milind-soni/tiptour-macos", - "evidenceUrl": "https://github.com/milind-soni/tiptour-macos/blob/52582467c883d66484542f3be8e259340eb524f1/README.md", - "language": "Swift", - "license": "Not declared", - "starsAtCapture": 627, + "id": "celestoai:celesto", + "name": "Celesto", + "owner": "CelestoAI", + "category": "developer-tools", + "repoUrl": "https://github.com/CelestoAI/celesto", + "evidenceUrl": "https://github.com/CelestoAI/celesto/blob/fff7bb567752baee4ce195fcb78b5ee5e4da889f/examples/pr-review-jev/models.py#L96", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/CelestoAI/celesto/blob/fff7bb567752baee4ce195fcb78b5ee5e4da889f/examples/pr-review-jev/models.py#L96" + }, + "language": "", + "license": "Apache-2.0", + "starsAtCapture": 946, "summary": { - "en": "A local macOS computer-use companion driven by Jev or Gemini Live.", - "zh": "由 JEV 或 Gemini Live 驱动的本地 macOS 电脑操作伴侣。", - "ja": "JEV または Gemini Live によって駆動されるローカル macOS コンピューター使用コンパニオン。" + "en": "A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.", + "zh": "Celesto 的 PR 审查示例在沙盒中准备检查，再比较普通模型与 Jev 对候选问题的判断。", + "ja": "Celesto PR レビューの例では、サンドボックス チェックを準備し、候補となる結果について一般的なモデルと JEV を比較します。" }, "decision": { - "en": "Jev chooses pointer actions from locally parsed screen targets.", - "zh": "JEV 从本地解析出的屏幕目标中选择指针动作。", - "ja": "JEV は、ローカルで解析された画面ターゲットからポインター アクションを選択します。" + "en": "Judges whether a finding was introduced by the change, is supported and merits a fix.", + "zh": "检查疑似问题是否由当前变更引入、是否有证据、是否值得修复。", + "ja": "調査結果が変更によってもたらされたものであるか、サポートされているか、修正に値するかどうかを判断します。" }, "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/milindlabs/status/2101260711645372886", - "author": "@milindlabs", - "views": 54827 - } + "runtimeVerified": false }, { - "id": "kev", - "name": "Kev 0.5B", - "owner": "jaredpalmer", - "category": "open-models", - "repoUrl": "https://github.com/jaredpalmer/kev", - "evidenceUrl": "https://github.com/jaredpalmer/kev/blob/20fa6268c8ceb226530be2fb5266ab2c36b37724/README.md", - "language": "Python", - "license": "Apache-2.0", - "starsAtCapture": 1530, + "id": "bastani-inc:atomic", + "name": "Atomic", + "owner": "bastani-inc", + "category": "routing-optimization", + "repoUrl": "https://github.com/bastani-inc/atomic", + "evidenceUrl": "https://github.com/bastani-inc/atomic/blob/33ca4ccb5f39488aeba67c0212a52a31cd14059d/packages/coding-agent/src/core/structured-output/jev.ts", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/bastani-inc/atomic/blob/33ca4ccb5f39488aeba67c0212a52a31cd14059d/packages/coding-agent/src/core/structured-output/jev.ts" + }, + "language": "TypeScript", + "license": "Custom license", + "starsAtCapture": 809, "summary": { - "en": "A tiny trainable Jev-like decision model based on Qwen2.5-0.5B.", - "zh": "基于 Qwen2.5-0.5B、可在 MacBook 上训练运行的轻量决策模型。", - "ja": "Qwen2.5-0.5B に基づく、小さなトレーニング可能な JEV のような意思決定モデル。" + "en": "An optional Jev decision backend in the Atomic coding Agent for bounded structured choices such as routing.", + "zh": "Atomic 编程 Agent 的可选 Jev 决策后端，为路由等流程提供受限的结构化选择。", + "ja": "ルーティングなど、範囲を限定した構造化選択に使える Atomic コーディング Agent の任意 JEV バックエンド。" }, "decision": { - "en": "Exposes a TypeSafe-compatible API for bounded local choices and scores.", - "zh": "通过 TypeSafe 兼容接口完成有边界的本地选择与评分。", - "ja": "制限されたローカルの選択肢とスコア用の TypeSafe 互換 API を公開します。" + "en": "Sends predefined questions to Jev and decodes answers for callers; regular models still generate code.", + "zh": "将预定义的问题交给 Jev，解码答案后由调用方应用；常规模型仍负责生成代码。", + "ja": "事前定義された質問を JEV に送信し、呼び出し元の回答をデコードします。通常のモデルでもコードが生成されます。" }, "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/jaredpalmer/status/2101028325472841920", - "author": "@jaredpalmer", - "views": 165852 - } + "runtimeVerified": false }, { - "id": "nimble", - "name": "Nimble", - "owner": "bespokelabsai", - "category": "open-models", - "repoUrl": "https://github.com/bespokelabsai/nimble", - "evidenceUrl": "https://github.com/bespokelabsai/nimble/blob/35fe1f4fdbc64fa3dbbf5ac0042f3f5680c1ad28/README.md", - "language": "Python", + "id": "vercel-ai-cli", + "name": "AI CLI", + "owner": "vercel-labs", + "category": "developer-tools", + "repoUrl": "https://github.com/vercel-labs/ai-cli", + "evidenceUrl": "https://github.com/vercel-labs/ai-cli/blob/6a0ed5d04ea60ee536029d469499b82898d1b214/skills/ai-cli/SKILL.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/vercel-labs/ai-cli/blob/6a0ed5d04ea60ee536029d469499b82898d1b214/skills/ai-cli/SKILL.md" + }, + "language": "TypeScript", "license": "Not declared", - "starsAtCapture": 1357, + "starsAtCapture": 808, "summary": { - "en": "An open toolkit for local typed decisions, data curation, and evaluation.", - "zh": "面向本地类型化决策、数据整理与评测的开放工具包。", - "ja": "ローカルでの型付き意思決定、データキュレーション、評価に使えるオープンツールキット。" + "en": "A terminal generator CLI that ships with an agent skill for creating content from the command line.", + "zh": "终端生成 CLI，并附带可从命令行创作内容的 Agent Skill。", + "ja": "ターミナルからコンテンツ生成するための Agent Skill 付き CLI。" }, "decision": { - "en": "Explores open local classifiers for bounded judgments and comparable evaluations.", - "zh": "探索用于有限判断的开放本地分类器与可比较评测。", - "ja": "境界の明確な判断と比較可能な評価に使える、オープンなローカル分類器を検証します。" + "en": "Chooses generation steps and skill instructions before local CLI execution.", + "zh": "在本地 CLI 执行前选择生成步骤与 Skill 说明。", + "ja": "ローカル CLI 実行前に生成手順と Skill 指示を選びます。" }, "verification": "source-reviewed", - "runtimeVerified": false, + "runtimeVerified": false + }, + { + "id": "yibie-awesome-jev", + "name": "Awesome JEV (yibie)", + "owner": "yibie", + "category": "developer-tools", + "repoUrl": "https://github.com/yibie/awesome-jev", + "evidenceUrl": "https://github.com/yibie/awesome-jev/blob/a42aea88b30aeb62b3f165395f15336853e01863/README.md", "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/aisearchio/status/2101394114176806966", - "author": "@aisearchio", - "views": 63276 - } + "type": "github", + "label": "GitHub source", + "url": "https://github.com/yibie/awesome-jev/blob/a42aea88b30aeb62b3f165395f15336853e01863/README.md" + }, + "language": "Python", + "license": "Unknown", + "starsAtCapture": 805, + "summary": { + "en": "A large community directory of public JEV projects, integrations, and discussions.", + "zh": "收录公开 JEV 项目、集成与讨论的大型社区目录。", + "ja": "公開 JEV プロジェクト、連携、議論をまとめた大規模コミュニティ目录。" + }, + "decision": { + "en": "Organizes the ecosystem into browsable implementation and discussion groups.", + "zh": "把生态项目按实现与讨论类型整理为可浏览目录。", + "ja": "実装と議論を参照しやすい分類に整理します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "awesome-jev-by-typesafe", + "name": "Awesome JEV by TypeSafe", + "owner": "Anil-matcha", + "category": "developer-tools", + "repoUrl": "https://github.com/Anil-matcha/awesome-jev-by-typesafe", + "evidenceUrl": "https://github.com/Anil-matcha/awesome-jev-by-typesafe/blob/0f4a1eadcdd70f4fc1cf8eadcf72794dfe416095/docs/jev-use-case-playbook.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/Anil-matcha/awesome-jev-by-typesafe/blob/0f4a1eadcdd70f4fc1cf8eadcf72794dfe416095/docs/jev-use-case-playbook.md" + }, + "language": "Python", + "license": "MIT", + "starsAtCapture": 742, + "summary": { + "en": "An evidence-backed playbook of JEV use cases, patterns, prompts, and starter code.", + "zh": "有证据支撑的 JEV 用例、模式、提示词与起步代码手册。", + "ja": "根拠付きの JEV ユースケース・パターン・プロンプト・スターター集。" + }, + "decision": { + "en": "Helps builders pick which typed decision pattern fits a product workflow.", + "zh": "帮助开发者判断哪种类型化决策模式适合自己的产品流程。", + "ja": "どの型付き意思決定パターンが製品フローに合うかを選ぶ助けになります。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "awlevin:typesafe-computer-use", + "name": "TypeSafe Computer Use", + "owner": "awlevin", + "category": "browser-computer-use", + "repoUrl": "https://github.com/awlevin/typesafe-computer-use", + "evidenceUrl": "https://github.com/awlevin/typesafe-computer-use/blob/cc7b5066ae1a07b5e3182e8f87a9b5b6dfdcffc1/typesafe_computer_use/decide.py", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/awlevin/typesafe-computer-use/blob/cc7b5066ae1a07b5e3182e8f87a9b5b6dfdcffc1/typesafe_computer_use/decide.py" + }, + "language": "Python", + "license": "MIT", + "starsAtCapture": 693, + "summary": { + "en": "Builds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.", + "zh": "用 OCR 和界面状态构造候选动作，让 Jev 决定如何操作 macOS，需要写文字时再调用文本模型。", + "ja": "JEV の OCR および UI 状態から候補アクションを構築して macOS を制御し、書き込みが必要な場合にのみテキスト モデルを呼び出します。" + }, + "decision": { + "en": "Selects the next step from deterministically extracted controls and actions before desktop execution.", + "zh": "从确定性提取的控件与动作中选择下一步，执行器操作桌面。", + "ja": "デスクトップの実行前に、決定的に抽出されたコントロールとアクションから次のステップを選択します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "uezo:aiavatarkit", + "name": "Aiavatarkit", + "owner": "uezo", + "category": "interfaces", + "repoUrl": "https://github.com/uezo/aiavatarkit", + "evidenceUrl": "https://github.com/uezo/aiavatarkit/blob/38b617b8b9269939734e70ef503d7ea6976acdbd/aiavatar/sts/vad/turn_end_gates/jev.py#L172", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/uezo/aiavatarkit/blob/38b617b8b9269939734e70ef503d7ea6976acdbd/aiavatar/sts/vad/turn_end_gates/jev.py#L172" + }, + "language": "", + "license": "Apache-2.0", + "starsAtCapture": 678, + "summary": { + "en": "An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts.", + "zh": "AIAvatarKit 的可选 Jev 组件根据转写内容判断用户是否结束发言。", + "ja": "オプションの AIAvatarKit コンポーネントは、JEV を使用して音声トランスクリプトからターン終了を判断します。" + }, + "decision": { + "en": "Assesses utterance completeness and whether the user is likely to continue speaking.", + "zh": "评估当前话语是否完整、是否准备继续说，并影响轮次结束门槛。", + "ja": "発話の完全性と、ユーザーが発話を続ける可能性があるかどうかを評価します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "kentcdodds:kody", + "name": "Kody", + "owner": "kentcdodds", + "category": "search-data", + "repoUrl": "https://github.com/kentcdodds/kody", + "evidenceUrl": "https://github.com/kentcdodds/kody/blob/ed9275186dc817530dd2289e62c208ac3809391f/packages/worker/src/mcp/tools/search-jev-rerank.ts", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/kentcdodds/kody/blob/ed9275186dc817530dd2289e62c208ac3809391f/packages/worker/src/mcp/tools/search-jev-rerank.ts" + }, + "language": "TypeScript", + "license": "FSL-1.1-ALv2", + "starsAtCapture": 659, + "summary": { + "en": "Optional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.", + "zh": "可选的二段检索：先扩大混合召回，再用 Cloudflare Workers AI 上的 `typesafe/jev` Score 重排。", + "ja": "オプションの第 2 段階の検索: ハイブリッド プールを拡大し、Workers AI typesafe/jev を使用して候補者をスコア再ランク付けします。" + }, + "decision": { + "en": "Sends a Score question per candidate, reorders and drops low scores; the model id is typesafe/jev.", + "zh": "对每个候选发 Score 问题，按分数重排并丢掉低分结果；模型 ID 为 `typesafe/jev`。", + "ja": "候補者ごとにスコアの質問を送信し、並べ替えて低いスコアを削除します。モデル ID は typesafe/jev です。" + }, + "verification": "source-reviewed", + "runtimeVerified": false }, { "id": "localjev", @@ -951,752 +1229,908 @@ } }, { - "id": "jev-experiments", - "name": "Jev Experiments", - "owner": "dabit3", - "category": "search-data", - "repoUrl": "https://github.com/dabit3/jev-experiments", - "evidenceUrl": "https://github.com/dabit3/jev-experiments/tree/c469e5bfdc73eb3e1999bba2569e66b579a970fd/agent-assist", - "language": "TypeScript", + "id": "tiptour-macos", + "name": "TipTour macOS", + "owner": "milind-soni", + "category": "interfaces", + "repoUrl": "https://github.com/milind-soni/tiptour-macos", + "evidenceUrl": "https://github.com/milind-soni/tiptour-macos/blob/52582467c883d66484542f3be8e259340eb524f1/README.md", + "language": "Swift", "license": "Not declared", - "starsAtCapture": 352, + "starsAtCapture": 627, "summary": { - "en": "Small Jev experiments including intent search and agent-assist flows.", - "zh": "包含意图搜索与 Agent Assist 流程的一组 JEV 实验。", - "ja": "インテント検索やエージェント支援フローを含む小規模な JEV 実験。" + "en": "A local macOS computer-use companion driven by Jev or Gemini Live.", + "zh": "由 JEV 或 Gemini Live 驱动的本地 macOS 电脑操作伴侣。", + "ja": "JEV または Gemini Live によって駆動されるローカル macOS コンピューター使用コンパニオン。" }, "decision": { - "en": "Uses fast intent judgments after retrieval instead of asking a large model to inspect everything.", - "zh": "在初步召回后快速判断意图，避免让大模型通读全部内容。", - "ja": "大規模なモデルにすべてを検査させる代わりに、取得後に迅速な意図判断を使用します。" + "en": "Jev chooses pointer actions from locally parsed screen targets.", + "zh": "JEV 从本地解析出的屏幕目标中选择指针动作。", + "ja": "JEV は、ローカルで解析された画面ターゲットからポインター アクションを選択します。" }, "verification": "source-reviewed", "runtimeVerified": false, "source": { "type": "x", "label": "Original X case", - "url": "https://x.com/dabit3/status/2100960281769738433", - "author": "@dabit3", - "views": 131659 + "url": "https://x.com/milindlabs/status/2101260711645372886", + "author": "@milindlabs", + "views": 54827 } }, { - "id": "tax-doc-classifier", - "name": "Tax Document Classifier", - "owner": "kyotofin", - "category": "search-data", - "repoUrl": "https://github.com/kyotofin/tax-doc-classifier", - "evidenceUrl": "https://github.com/kyotofin/tax-doc-classifier/blob/6afcf701395466d7c936ec8178daf017b9d96b0c/src/backend.ts", - "language": "TypeScript", - "license": "Apache-2.0", - "starsAtCapture": 314, + "id": "agentiloop:agent", + "name": "Agent", + "owner": "AgentiLoop", + "category": "safety-review", + "repoUrl": "https://github.com/AgentiLoop/Agent", + "evidenceUrl": "https://github.com/AgentiLoop/Agent/blob/078f87ceca1d1190cc73706ac8ec16442e766a27/README.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/AgentiLoop/Agent/blob/078f87ceca1d1190cc73706ac8ec16442e766a27/README.md" + }, + "language": "Swift", + "license": "MIT", + "starsAtCapture": 618, "summary": { - "en": "Classifies extracted tax-document pages against a fixed IRS form catalogue.", - "zh": "把税务文档页面归入预先定义的 IRS 表格目录。", - "ja": "抽出された税務書類のページを固定 IRS フォーム カタログに基づいて分類します。" + "en": "An optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.", + "zh": "原生 macOS Agent 内的可选 Jev 命令风险顾问，配有 TypeSafeKit 客户端。", + "ja": "TypeSafeKit クライアントを使用した、ネイティブ macOS エージェント内のオプションの JEV コマンド リスク アドバイザ。" }, "decision": { - "en": "Returns form type, page type, and confidence while ingestion stays deterministic.", - "zh": "返回表格类型、页面类型与置信度，文档入库仍由确定性代码控制。", - "ja": "取り込みが決定的なままである間、フォーム タイプ、ページ タイプ、および信頼度を返します。" + "en": "Adds a destructive-risk judgment after local shell checks and refuses commands above the configured threshold.", + "zh": "对已通过本地规则的 Shell 命令追加破坏性判断，达到配置阈值时拒绝。", + "ja": "ローカル シェルのチェック後に破壊的リスクの判定を追加し、設定されたしきい値を超えるコマンドを拒否します。" }, "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/nedwize/status/2100973868324417852", - "author": "@nedwize", - "views": 223890 - } + "runtimeVerified": false }, { - "id": "abide", - "name": "Abide", - "owner": "coldteadotai", - "category": "safety-review", - "repoUrl": "https://github.com/coldteadotai/abide", - "evidenceUrl": "https://github.com/coldteadotai/abide/blob/ec3352e873163b74aca1ac9cf3bd0ea69a97723a/README.md", - "language": "TypeScript", - "license": "MIT", - "starsAtCapture": 199, + "id": "v-modal-awesome-jev-tools", + "name": "Awesome JEV Tools", + "owner": "v-modal", + "category": "developer-tools", + "repoUrl": "https://github.com/v-modal/awesome-jev-tools", + "evidenceUrl": "https://github.com/v-modal/awesome-jev-tools/blob/f117e0c368d6e293bf5fdf99244a1173a6dc2ae0/README.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/v-modal/awesome-jev-tools/blob/f117e0c368d6e293bf5fdf99244a1173a6dc2ae0/README.md" + }, + "language": "", + "license": "Unknown", + "starsAtCapture": 599, "summary": { - "en": "A coding-agent rule layer for constraints that ordinary linters cannot express.", - "zh": "为普通 Linter 难以表达的项目规则增加 Agent 级约束。", - "ja": "通常のリンターでは表現できない制約を扱う、コーディング Agent 向けルール層。" + "en": "A curated directory focused on tools built for JEV and TypeSafe System One.", + "zh": "聚焦 JEV 与 TypeSafe System One 工具的精选目录。", + "ja": "JEV と TypeSafe System One 向けツールのキュレーション目录。" }, "decision": { - "en": "Scores each agent turn against semantic rules and returns targeted corrections.", - "zh": "逐轮对照语义规则评分，并把需要修正的约束返回给 Agent。", - "ja": "セマンティック ルールに対してエージェントが反抗するたびにスコアを付け、対象を絞った修正を返します。" + "en": "Surfaces practical tools by integration shape and use case.", + "zh": "按集成方式与使用场景筛选实用工具。", + "ja": "連携方式と用途別に実用ツールを紹介します。" }, "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/OhansEmmanuel/status/2101034822760288452", - "author": "@OhansEmmanuel", - "views": 108458 - } + "runtimeVerified": false }, { - "id": "jev-align", - "name": "jev-align", - "owner": "sutro-sh", - "category": "safety-review", - "repoUrl": "https://github.com/sutro-sh/jev-align", - "evidenceUrl": "https://github.com/sutro-sh/jev-align/blob/49753df924d30c0d3642b58e0b9b1e89921dc102/README.md", - "language": "Python", + "id": "agentjido:req_llm", + "name": "Req LLM", + "owner": "agentjido", + "category": "sdk-integrations", + "repoUrl": "https://github.com/agentjido/req_llm", + "evidenceUrl": "https://github.com/agentjido/req_llm/blob/9cb0ee7a0fea5f3520fc953911d352c93193615e/README.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/agentjido/req_llm/blob/9cb0ee7a0fea5f3520fc953911d352c93193615e/README.md" + }, + "language": "Elixir", "license": "Apache-2.0", - "starsAtCapture": 253, + "starsAtCapture": 580, "summary": { - "en": "A CLI for calibrating Jev classifiers from human examples with GEPA.", - "zh": "用人工正反例和 GEPA 校准 JEV 分类标准的 CLI。", - "ja": "GEPA を使用して人間の例から JEV 分類器を調整するための CLI。" + "en": "A TypeSafe provider for calling Jev through ReqLLM’s evaluate interface in Elixir.", + "zh": "ReqLLM 的 TypeSafe provider，让 Elixir 应用通过 evaluate 接口调用 Jev。", + "ja": "Elixir の ReqLLM 評価インターフェイスから JEV を呼び出す TypeSafe プロバイダー。" }, "decision": { - "en": "Optimizes the decision prompt against examples instead of relying on a generic criterion.", - "zh": "围绕明确样例优化判断标准，而不是依赖泛化提示词。", - "ja": "一般的な基準に依存するのではなく、例に基づいて決定プロンプトを最適化します。" + "en": "Sends state and questions, normalizes answers and retains the raw provider response.", + "zh": "提交状态与判断题，将答案放入统一响应对象，并保留原始 provider 数据。", + "ja": "状態と質問を送り、回答を正規化しつつ、プロバイダーの元レスポンスも保持します。" }, "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/sethkimmel3/status/2101357768640987302", - "author": "@sethkimmel3", - "views": 68757 - } + "runtimeVerified": false }, { - "id": "jeff", - "name": "Jeff", - "owner": "logan-markewich", - "category": "open-models", - "repoUrl": "https://github.com/logan-markewich/jeff", - "evidenceUrl": "https://github.com/logan-markewich/jeff/blob/34b32f99a727c47b679adde33f4702a001e02979/README.md", - "language": "Python", + "id": "bennykok:omg-dev", + "name": "Omg.dev", + "owner": "BennyKok", + "category": "browser-computer-use", + "repoUrl": "https://github.com/BennyKok/omg.dev", + "evidenceUrl": "https://github.com/BennyKok/omg.dev/blob/a00f56684a569ee417be787c148eaa9874946f2b/mobile/scripts/jev.ts", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/BennyKok/omg.dev/blob/a00f56684a569ee417be787c148eaa9874946f2b/mobile/scripts/jev.ts" + }, + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 183, + "starsAtCapture": 533, "summary": { - "en": "A self-hosted Jev-compatible service powered by GliFormer.", - "zh": "基于 GliFormer、可自托管的 JEV 兼容服务。", - "ja": "GliFormer を利用したセルフホスト型の JEV 互換サービス。" + "en": "An omg.dev mobile testing script can use Jev to read the accessibility tree and choose the next interaction.", + "zh": "omg.dev 的移动端测试脚本可让 Jev 读取可访问性树并选择下一步交互。", + "ja": "omg.dev モバイル テスト スクリプトは、JEV を使用してアクセシビリティ ツリーを読み取り、次のインタラクションを選択できます。" }, "decision": { - "en": "Preserves the decision API while running the classifier locally.", - "zh": "保留简洁的决策 API，同时在本地运行分类器。", - "ja": "分類子をローカルで実行している間、意思決定 API を保持します。" + "en": "Chooses controls and checks completion or blockage before the test runner operates the UI.", + "zh": "判断要操作的控件、步骤是否完成或是否受阻，再由测试执行器操作界面。", + "ja": "テスト ランナーが UI を操作する前に、コントロールを選択し、完了または障害をチェックします。" }, "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/LoganMarkewich/status/2101142971223781587", - "author": "@LoganMarkewich", - "views": 29163 - } + "runtimeVerified": false }, { - "id": "jev-semgrep", - "name": "jev-semgrep", - "owner": "uehaj", - "category": "search-data", - "repoUrl": "https://github.com/uehaj/jev-semgrep", - "evidenceUrl": "https://github.com/uehaj/jev-semgrep/blob/ba6ef50f85d0c5d6caa4db102ee4db4a08c85dd2/README.md", + "id": "jev-cu", + "name": "Jev CU", + "owner": "Sac-Y", + "category": "browser-computer-use", + "repoUrl": "https://github.com/Sac-Y/Jev-cu", + "evidenceUrl": "https://github.com/Sac-Y/Jev-cu/blob/38fb31de7dfe6209bbe6e04057c00c6e885ba577/scripts/jev-decide.mjs", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/Sac-Y/Jev-cu/blob/38fb31de7dfe6209bbe6e04057c00c6e885ba577/scripts/jev-decide.mjs" + }, "language": "JavaScript", "license": "Not declared", - "starsAtCapture": 122, + "starsAtCapture": 519, "summary": { - "en": "Meaning-based grep with multilingual AND, OR, NOT, and probability thresholds.", - "zh": "支持跨语言 AND、OR、NOT 与概率阈值的“按意思搜索”grep。", - "ja": "多言語の AND、OR、NOT、確率しきい値を使用した意味ベースの grep。" + "en": "Computer-use helpers that call JEV to decide the next UI action.", + "zh": "用 JEV 决定下一步界面动作的 Computer Use 辅助工具。", + "ja": "次の UI 操作を JEV に決めさせる Computer Use 補助ツール。" }, "decision": { - "en": "Scores whether each line satisfies a proposition, then applies grep controls locally.", - "zh": "判断每行是否满足命题，再由本地代码应用 grep 控制项。", - "ja": "各行が命題を満たすかどうかをスコアリングし、grep コントロールをローカルに適用します。" + "en": "Picks a bounded next action from observed UI state before local execution.", + "zh": "根据观察到的界面状态，在本地执行前选出有限下一步动作。", + "ja": "観測した UI 状態から、ローカル実行前に有限の次アクションを選びます。" }, "verification": "source-reviewed", - "runtimeVerified": false, + "runtimeVerified": false + }, + { + "id": "splash", + "name": "Splash", + "owner": "incoai", + "category": "open-models", + "repoUrl": "https://github.com/incoai/splash", + "evidenceUrl": "https://github.com/incoai/splash/blob/f53d5ab543a7accdc332c060fd594a693f33f529/README.md", "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/uehaj/status/2101198713834381716", - "author": "@uehaj", - "views": 81889 - } + "type": "github", + "label": "GitHub source", + "url": "https://github.com/incoai/splash/blob/f53d5ab543a7accdc332c060fd594a693f33f529/README.md" + }, + "language": "Python", + "license": "Apache-2.0", + "starsAtCapture": 506, + "summary": { + "en": "A local Apple Silicon inference engine oriented around decision-style models.", + "zh": "面向决策类模型的本地 Apple Silicon 推理引擎。", + "ja": "意思決定系モデル向けの Apple Silicon ローカル推論エンジン。" + }, + "decision": { + "en": "Runs local inference so apps can obtain typed judgments without a remote JEV hop.", + "zh": "在本地完成推理，让应用无需远程 JEV 也能拿到类型化判断。", + "ja": "ローカル推論で型付き判断を返し、遠隔 JEV なしでも使えるようにします。" + }, + "verification": "source-reviewed", + "runtimeVerified": false }, { - "id": "jev-gateway", - "name": "jev-gateway", - "owner": "vinilana", - "category": "agent-workflows", - "repoUrl": "https://github.com/vinilana/jev-gateway", - "evidenceUrl": "https://github.com/vinilana/jev-gateway/blob/9463952bf118773fb955427d2725a98f76546233/README.md", + "id": "thruwire:foreman", + "name": "Foreman", + "owner": "thruwire", + "category": "developer-tools", + "repoUrl": "https://github.com/thruwire/foreman", + "evidenceUrl": "https://github.com/thruwire/foreman/blob/209182dac7a3467033fd093ab4ca47d21279984a/src/foreman/foreman/jev.py", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/thruwire/foreman/blob/209182dac7a3467033fd093ab4ca47d21279984a/src/foreman/foreman/jev.py" + }, + "language": "Python", + "license": "MIT", + "starsAtCapture": 446, + "summary": { + "en": "An independent supervisor loop that reads worker diffs, logs and tests, asks Jev Nouls about stuck / off-track / verify, then applies a Python policy.", + "zh": "独立监督环读取编码工人的 diff、日志和测试，用 Jev Noul 判断卡住、跑偏、该验证，再由 Python 策略干预。", + "ja": "ワーカーの差分、ログ、テストを読み取り、スタック/オフトラック/検証について JEV Nouls に質問し、Python ポリシーを適用する独立したスーパーバイザー ループ。" + }, + "decision": { + "en": "AsyncTypeSafeClient.system_one with default jev-latest sends Noul questions for supervision.", + "zh": "`AsyncTypeSafeClient.system_one`，默认 `jev-latest`，对监督问题发 Noul。", + "ja": "デフォルトの jev-latest を使用する AsyncTypeSafeClient.system_one は、監視のために Noul の質問を送信します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "jev-review", + "name": "Jev Review", + "owner": "devagrawal09", + "category": "developer-tools", + "repoUrl": "https://github.com/devagrawal09/jev-review", + "evidenceUrl": "https://github.com/devagrawal09/jev-review/blob/31f89602797fb7bea007f8a480bf368bf564954e/src/review/judgments.ts#L38", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/devagrawal09/jev-review/blob/31f89602797fb7bea007f8a480bf368bf564954e/src/review/judgments.ts#L38" + }, "language": "TypeScript", "license": "MIT", - "starsAtCapture": 79, + "starsAtCapture": 438, "summary": { - "en": "A gateway for inserting Jev decisions into Claude Code and Codex tool flows.", - "zh": "把 JEV 判断接入 Claude Code 与 Codex 工具流程的网关。", - "ja": "JEV 決定を Claude Code および Codex ツール フローに挿入するためのゲートウェイ。" + "en": "Reviews a Git diff or a codebase in stages and displays review leads in a local dashboard.", + "zh": "分阶段检查 Git diff 或整个代码库，在本地面板里展示可复核的审查线索。", + "ja": "Git diff またはコードベースを段階的にレビューし、ローカル ダッシュボードにレビュー リードを表示します。" }, "decision": { - "en": "Delegates bounded tool-choice judgments while the coding agent owns the broader task.", - "zh": "把有限的工具选择判断分离出来，完整任务仍由编码 Agent 负责。", - "ja": "コーディングエージェントがより広範なタスクを所有する一方で、限定されたツール選択の判断を委任します。" + "en": "Judges risk, files, evidence regions, mechanisms and severity before rule-based reviewer routing.", + "zh": "依次判断风险、文件、证据片段、问题机制和严重程度，再按规则选择审查路径。", + "ja": "ルールベースのレビュー担当者ルーティングの前に、リスク、ファイル、証拠領域、メカニズム、重大度を判断します。" }, "verification": "source-reviewed", - "runtimeVerified": false, + "runtimeVerified": false + }, + { + "id": "featherless-ai:simple-jev", + "name": "Simple JEV", + "owner": "featherless-ai", + "category": "sdk-integrations", + "repoUrl": "https://github.com/featherless-ai/simple-jev", + "evidenceUrl": "https://github.com/featherless-ai/simple-jev/blob/0dd5396ffce671ab7c4bfc031506d8e558cf8d23/demos/jevpilot/src/simple-jev-api.js#L1-L85", "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/oviniciuslana/status/2101057880640127230", - "author": "@oviniciuslana", - "views": 53439 - } + "type": "github", + "label": "GitHub source", + "url": "https://github.com/featherless-ai/simple-jev/blob/0dd5396ffce671ab7c4bfc031506d8e558cf8d23/demos/jevpilot/src/simple-jev-api.js#L1-L85" + }, + "language": "Python", + "license": "Unknown", + "starsAtCapture": 428, + "summary": { + "en": "Adapter turning open LLM endpoints into Jev-compatible classification services without training a separate classifier head.", + "zh": "将任意开源大语言模型转化为分类器与 Jev 兼容端点的适配服务，无需额外训练专用分类头。", + "ja": "専用の分類ヘッドを学習せずに、公開 LLM エンドポイントを JEV 互換の分類サービスへ変換するアダプター。" + }, + "decision": { + "en": "Extracts log-probabilities of candidate tokens from model vocabulary logits, formatting them into standard Jev responses.", + "zh": "通过分析输入文本在模型词表中的 logits 分布，将候选项映射为标准 Jev 离散概率输出。", + "ja": "モデル語彙ロジットから候補トークンの対数確率を抽出し、標準の JEV 応答にフォーマットします。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "notque:vexjoy-agent", + "name": "Vexjoy Agent", + "owner": "notque", + "category": "routing-optimization", + "repoUrl": "https://github.com/notque/vexjoy-agent", + "evidenceUrl": "https://github.com/notque/vexjoy-agent/blob/ab51ee7da567e84f72f76d73b6e7b83cec5ef060/README.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/notque/vexjoy-agent/blob/ab51ee7da567e84f72f76d73b6e7b83cec5ef060/README.md" + }, + "language": "Python", + "license": "MIT", + "starsAtCapture": 421, + "summary": { + "en": "An optional Jev routing path that matches VexJoy requests to specialist Agents, skills and workflows.", + "zh": "给 VexJoy 的任务分派增加一条 Jev 路线。输入需求后，判断该选哪位专长 Agent、哪项技能和哪条工作流。", + "ja": "VexJoy リクエストを専門エージェント、スキル、ワークフローに照合するオプションの JEV ルーティング パス。" + }, + "decision": { + "en": "After deterministic routing guards, Jev judges the remaining candidates and required workflow components.", + "zh": "先判断是否需要路由，再从实际清单中选择候选；非法选择或调用失败交回原有流程。", + "ja": "確定的ルーティング ガードの後、JEV は残りの候補と必要なワークフロー コンポーネントを判断します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false }, { - "id": "hono-jev-router", - "name": "Hono Jev Router", - "owner": "yusukebe", - "category": "developer-tools", - "repoUrl": "https://github.com/yusukebe/hono-jev-router", - "evidenceUrl": "https://github.com/yusukebe/hono-jev-router/blob/04f6e103e1397bca659ab85c042011a1f14b679d/README.md", + "id": "smithers", + "name": "Smithers", + "owner": "smithersai", + "category": "agent-workflows", + "repoUrl": "https://github.com/smithersai/smithers", + "evidenceUrl": "https://github.com/smithersai/smithers/blob/394ada6a3fb815b4b62cfc7bc2242e238d42ff44/apps/server/src/jev.ts", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/smithersai/smithers/blob/394ada6a3fb815b4b62cfc7bc2242e238d42ff44/apps/server/src/jev.ts" + }, "language": "TypeScript", "license": "MIT", - "starsAtCapture": 45, + "starsAtCapture": 418, "summary": { - "en": "A semantic Hono router that matches HTTP requests by meaning.", - "zh": "不只按 method/path，而是按请求语义匹配处理器的 Hono 路由器。", - "ja": "意味によって HTTP リクエストを照合するセマンティック Hono ルーター。" + "en": "An agentic TypeScript workflow framework with a first-class JEV classify path.", + "zh": "以 TypeScript 配置定义工作流的 Agent 框架，内置 JEV 分类路径。", + "ja": "TypeScript 設定でワークフローを定義し、JEV 分類パスを持つエージェント枠組み。" }, "decision": { - "en": "Jev chooses among declared routes; Hono still owns execution and response handling.", - "zh": "JEV 从已声明路由中选择，执行和响应仍由 Hono 控制。", - "ja": "JEV は宣言されたルートの中から選択します。 Hono は依然として実行と応答の処理を所有しています。" + "en": "Classifies workflow steps or review verdicts through a dedicated JEV relay.", + "zh": "通过专用 JEV 中继对工作流步骤或审查结论做分类。", + "ja": "専用の JEV 中継でワークフロー手順やレビュー判定を分類します。" }, "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/yusukebe/status/2100871075743859182", - "author": "@yusukebe", - "views": 113075 - } + "runtimeVerified": false }, { - "id": "live-jev", - "name": "Live Jev", - "owner": "okinaaudio", - "category": "interfaces", - "repoUrl": "https://github.com/okinaaudio/live-jev", - "evidenceUrl": "https://github.com/okinaaudio/live-jev/blob/ecba7e01d5ff01a1e84d6bc4388245145338ed64/README.md", - "language": "Python", + "id": "awesome-typesafe", + "name": "Awesome TypeSafe", + "owner": "AbdelStark", + "category": "developer-tools", + "repoUrl": "https://github.com/AbdelStark/awesome-typesafe", + "evidenceUrl": "https://github.com/AbdelStark/awesome-typesafe/blob/d44dc0a1e26d41bc7f543d39b4b62ae5cb9f13c8/README.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/AbdelStark/awesome-typesafe/blob/d44dc0a1e26d41bc7f543d39b4b62ae5cb9f13c8/README.md" + }, + "language": "CSS", "license": "MIT", - "starsAtCapture": 38, + "starsAtCapture": 414, "summary": { - "en": "Controls Ableton Live from short Japanese or English commands.", - "zh": "用一句日语或英语命令控制 Ableton Live。", - "ja": "日本語または英語の短いコマンドから Ableton Live をコントロールします。" + "en": "A curated list of official and community resources for TypeSafe, System One, and JEV.", + "zh": "TypeSafe、System One 与 JEV 的官方与社区资源精选列表。", + "ja": "TypeSafe・System One・JEV の公式／コミュニティ資源をまとめたキュレーション一覧。" }, "decision": { - "en": "Jev maps the instruction to a bounded DAW action before local automation executes it.", - "zh": "JEV 把指令映射到有限的 DAW 动作，再由本地自动化执行。", - "ja": "JEV は、ローカル オートメーションが実行する前に、その命令を制限された DAW アクションにマップします。" + "en": "Surfaces which projects and docs are worth opening when building with System One.", + "zh": "帮你判断做 System One 时该先打开哪些项目与文档。", + "ja": "System One 開発時に開くべきプロジェクト／ドキュメントを示します。" }, "verification": "source-reviewed", - "runtimeVerified": false, - "source": { - "type": "x", - "label": "Original X case", - "url": "https://x.com/okinaaudio/status/2101156959546450049", - "author": "@okinaaudio", - "views": 85650 - } + "runtimeVerified": false }, { - "id": "jegrep", - "name": "jegrep", - "owner": "can1357", - "category": "search-data", - "repoUrl": "https://github.com/can1357/jegrep", - "evidenceUrl": "https://github.com/can1357/jegrep/blob/a280f14f6da8163bde67e0c49f58b23517a02882/src/jev.rs", - "language": "Rust", + "id": "classifier-dev", + "name": "Classifier.dev", + "owner": "mrmps", + "category": "sdk-integrations", + "repoUrl": "https://github.com/mrmps/classifier-dev", + "evidenceUrl": "https://github.com/mrmps/classifier-dev/blob/33ca63816f2bc7e93c3f2d0715f7896500370739/src/jev.ts", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/mrmps/classifier-dev/blob/33ca63816f2bc7e93c3f2d0715f7896500370739/src/jev.ts" + }, + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 57, + "starsAtCapture": 396, "summary": { - "en": "Semantic grep for live code trees: describe what you need, get files and original line ranges without building an index.", - "zh": "面向实时代码树的语义 grep：用自然语言描述目标，无需建索引即可返回文件与原始行号范围。", - "ja": "ライブ コード ツリーのセマンティック grep: 必要なものを記述し、インデックスを作成せずにファイルと元の行範囲を取得します。" + "en": "A zero-shot classification service with JEV as its primary typed-decision backend.", + "zh": "以 JEV 为主要类型化决策后端的零样本分类服务。", + "ja": "JEV を主要な型付き判断バックエンドに使うゼロショット分類サービス。" }, "decision": { - "en": "JEV scores folders, files, and bounded code passages; local search strategies manage budgets, thresholds, and fallbacks.", - "zh": "JEV 为目录、文件和有限代码片段评分，本地搜索策略负责预算、阈值与回退。", - "ja": "JEV は、フォルダー、ファイル、および制限されたコードパッセージをスコアリングします。ローカル検索戦略は、予算、しきい値、およびフォールバックを管理します。" + "en": "Classifies labels and dimensions, with explicit fallback and observability around JEV calls.", + "zh": "用 JEV 判断标签与维度，并提供明确的回退与可观测性。", + "ja": "JEV でラベルと次元を分類し、明示的なフォールバックと観測性を備えます。" }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "minecraft-agent-jev", + "name": "Astra + JEV Minecraft Agent", + "owner": "rmalde", + "category": "domain-tools", + "repoUrl": "https://github.com/rmalde/minecraft-agent", + "evidenceUrl": "https://github.com/rmalde/minecraft-agent/blob/78b40ed59514e5e2abde33a05ce398ecb2c39e05/models.mjs", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/can1357/jegrep/blob/a280f14f6da8163bde67e0c49f58b23517a02882/src/jev.rs" + "url": "https://github.com/rmalde/minecraft-agent/blob/78b40ed59514e5e2abde33a05ce398ecb2c39e05/models.mjs" + }, + "language": "JavaScript", + "license": "Unknown", + "starsAtCapture": 395, + "summary": { + "en": "A Minecraft agent where a planner sets objectives and JEV selects legal game actions.", + "zh": "由规划模型设定目标、JEV 选择合法游戏动作的 Minecraft Agent。", + "ja": "プランナーが目標を定め、JEV が合法なゲーム操作を選ぶ Minecraft Agent。" + }, + "decision": { + "en": "Chooses one available action from observed game state and planner objectives.", + "zh": "根据游戏状态与规划目标，从可用动作中选择一个。", + "ja": "ゲーム状態と計画目標から利用可能な操作を 1 つ選びます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "jev-reviewer", - "name": "Jev Reviewer", - "owner": "choxos", - "category": "safety-review", - "repoUrl": "https://github.com/choxos/jev-reviewer", - "evidenceUrl": "https://github.com/choxos/jev-reviewer/blob/da15868cdca5e64555e6643243a52ea71f60cf3b/README.md", - "language": "JavaScript", - "license": "MIT", - "starsAtCapture": 30, + "id": "jev-experiments", + "name": "Jev Experiments", + "owner": "dabit3", + "category": "search-data", + "repoUrl": "https://github.com/dabit3/jev-experiments", + "evidenceUrl": "https://github.com/dabit3/jev-experiments/tree/c469e5bfdc73eb3e1999bba2569e66b579a970fd/agent-assist", + "language": "TypeScript", + "license": "Not declared", + "starsAtCapture": 352, "summary": { - "en": "Extracts review evidence from research papers with quotes and page references.", - "zh": "从研究论文中提取系统综述证据，并保留原文引用与页码。", - "ja": "研究論文から引用や参照ページを含むレビュー証拠を抽出します。" + "en": "Small Jev experiments including intent search and agent-assist flows.", + "zh": "包含意图搜索与 Agent Assist 流程的一组 JEV 实验。", + "ja": "インテント検索やエージェント支援フローを含む小規模な JEV 実験。" }, "decision": { - "en": "Jev finds passages matching a field; the reviewer verifies every extracted claim.", - "zh": "JEV 找出符合审查字段的段落，每条结果仍由研究者核验。", - "ja": "JEV は、フィールドに一致するパッセージを検索します。レビュー担当者は、抽出されたすべてのクレームを検証します。" + "en": "Uses fast intent judgments after retrieval instead of asking a large model to inspect everything.", + "zh": "在初步召回后快速判断意图，避免让大模型通读全部内容。", + "ja": "大規模なモデルにすべてを検査させる代わりに、取得後に迅速な意図判断を使用します。" }, "verification": "source-reviewed", "runtimeVerified": false, "source": { "type": "x", "label": "Original X case", - "url": "https://x.com/ASofiMahmudi/status/2100985031703269425", - "author": "@ASofiMahmudi", - "views": 20563 + "url": "https://x.com/dabit3/status/2100960281769738433", + "author": "@dabit3", + "views": 131659 } }, { - "id": "celestoai:celesto", - "name": "Celesto", - "owner": "CelestoAI", - "category": "developer-tools", - "repoUrl": "https://github.com/CelestoAI/celesto", - "evidenceUrl": "https://github.com/CelestoAI/celesto/blob/fff7bb567752baee4ce195fcb78b5ee5e4da889f/examples/pr-review-jev/models.py#L96", + "id": "superagents-lab:jev-search", + "name": "JEV Search", + "owner": "superagents-lab", + "category": "search-data", + "repoUrl": "https://github.com/superagents-lab/jev-search", + "evidenceUrl": "https://github.com/superagents-lab/jev-search/blob/522868762f0637b20bf533f136e930cceb83b9f3/src/lib/typesafe.ts#L48", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/CelestoAI/celesto/blob/fff7bb567752baee4ce195fcb78b5ee5e4da889f/examples/pr-review-jev/models.py#L96" + "url": "https://github.com/superagents-lab/jev-search/blob/522868762f0637b20bf533f136e930cceb83b9f3/src/lib/typesafe.ts#L48" }, "language": "", - "license": "Apache-2.0", - "starsAtCapture": 946, + "license": "MIT", + "starsAtCapture": 352, "summary": { - "en": "A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.", - "zh": "Celesto 的 PR 审查示例在沙盒中准备检查，再比较普通模型与 Jev 对候选问题的判断。", - "ja": "Celesto PR レビューの例では、サンドボックス チェックを準備し、候補となる結果について一般的なモデルと JEV を比較します。" + "en": "Searches the web with Jev choosing sources and time ranges, then ranking returned links.", + "zh": "用自然语言搜网页：Jev 选择搜索来源和时间范围，再给返回的链接排序。", + "ja": "JEV を使用して Web を検索し、ソースと時間範囲を選択し、返されたリンクをランク付けします。" }, "decision": { - "en": "Judges whether a finding was introduced by the change, is supported and merits a fix.", - "zh": "检查疑似问题是否由当前变更引入、是否有证据、是否值得修复。", - "ja": "調査結果が変更によってもたらされたものであるか、サポートされているか、修正に値するかどうかを判断します。" + "en": "Judges search intent, source and time settings, and relevance of individual results.", + "zh": "判断查询意图、来源与时间条件，并给各条搜索结果打相关性分数。", + "ja": "審査員は、検索の意図、ソースと時間の設定、個々の結果の関連性を判断します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "bastani-inc:atomic", - "name": "Atomic", - "owner": "bastani-inc", + "id": "hermes-jev-skills", + "name": "Hermes JEV Skills", + "owner": "kerpopule", "category": "routing-optimization", - "repoUrl": "https://github.com/bastani-inc/atomic", - "evidenceUrl": "https://github.com/bastani-inc/atomic/blob/33ca4ccb5f39488aeba67c0212a52a31cd14059d/packages/coding-agent/src/core/structured-output/jev.ts", + "repoUrl": "https://github.com/kerpopule/hermes-jev-skills", + "evidenceUrl": "https://github.com/kerpopule/hermes-jev-skills/blob/a5d89014fbeca5102c5e7ccd3915afcd856505d8/jevkit/choose.py", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/bastani-inc/atomic/blob/33ca4ccb5f39488aeba67c0212a52a31cd14059d/packages/coding-agent/src/core/structured-output/jev.ts" + "url": "https://github.com/kerpopule/hermes-jev-skills/blob/a5d89014fbeca5102c5e7ccd3915afcd856505d8/jevkit/choose.py" }, - "language": "TypeScript", - "license": "Custom license", - "starsAtCapture": 809, + "language": "Python", + "license": "MIT", + "starsAtCapture": 335, "summary": { - "en": "An optional Jev decision backend in the Atomic coding Agent for bounded structured choices such as routing.", - "zh": "Atomic 编程 Agent 的可选 Jev 决策后端，为路由等流程提供受限的结构化选择。", - "ja": "ルーティングなど、範囲を限定した構造化選択に使える Atomic コーディング Agent の任意 JEV バックエンド。" + "en": "JEV-powered routing, memory, compaction, skill selection, and computer/browser use for Hermes agents.", + "zh": "为 Hermes Agent 提供 JEV 驱动的路由、记忆、压缩、Skill 选择与电脑/浏览器操作。", + "ja": "Hermes エージェント向けに、JEV 駆動のルーティング・記憶・圧縮・Skill 選択・PC/ブラウザ操作。" }, "decision": { - "en": "Sends predefined questions to Jev and decodes answers for callers; regular models still generate code.", - "zh": "将预定义的问题交给 Jev，解码答案后由调用方应用；常规模型仍负责生成代码。", - "ja": "事前定義された質問を JEV に送信し、呼び出し元の回答をデコードします。通常のモデルでもコードが生成されます。" + "en": "Chooses models, skills, or next computer actions from bounded JEV questions.", + "zh": "用有限 JEV 问题选择模型、Skill 或下一步电脑动作。", + "ja": "有限の JEV 質問でモデル・Skill・次の PC 操作を選びます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "uezo:aiavatarkit", - "name": "Aiavatarkit", - "owner": "uezo", - "category": "interfaces", - "repoUrl": "https://github.com/uezo/aiavatarkit", - "evidenceUrl": "https://github.com/uezo/aiavatarkit/blob/38b617b8b9269939734e70ef503d7ea6976acdbd/aiavatar/sts/vad/turn_end_gates/jev.py#L172", + "id": "wrongstack:wrongstack", + "name": "WrongStack", + "owner": "WrongStack", + "category": "routing-optimization", + "repoUrl": "https://github.com/WrongStack/WrongStack", + "evidenceUrl": "https://github.com/WrongStack/WrongStack/blob/4cf97c0aa4f855751949ee8e99c719d06f4c26e0/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/uezo/aiavatarkit/blob/38b617b8b9269939734e70ef503d7ea6976acdbd/aiavatar/sts/vad/turn_end_gates/jev.py#L172" + "url": "https://github.com/WrongStack/WrongStack/blob/4cf97c0aa4f855751949ee8e99c719d06f4c26e0/README.md" }, - "language": "", - "license": "Apache-2.0", - "starsAtCapture": 678, + "language": "TypeScript", + "license": "MIT", + "starsAtCapture": 329, "summary": { - "en": "An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts.", - "zh": "AIAvatarKit 的可选 Jev 组件根据转写内容判断用户是否结束发言。", - "ja": "オプションの AIAvatarKit コンポーネントは、JEV を使用して音声トランスクリプトからターン終了を判断します。" + "en": "An optional Jev dispatch classifier for choosing among WrongStack specialist Agents.", + "zh": "给 WrongStack 编程 Agent 增加一个可选分派助手。遇到多个相近的专长 Agent 时，用 Jev 判断谁更适合当前任务。", + "ja": "WrongStack の専門 Agent から担当を選ぶための、任意で使える JEV ディスパッチ分類器。" }, "decision": { - "en": "Assesses utterance completeness and whether the user is likely to continue speaking.", - "zh": "评估当前话语是否完整、是否准备继续说，并影响轮次结束门槛。", - "ja": "発話の完全性と、ユーザーが発話を続ける可能性があるかどうかを評価します。" + "en": "Jev evaluates the task against eligible specialists; local dispatch rules use the result.", + "zh": "从候选角色中选一个，同时判断有没有任何候选真正适合；不合适时交回原有策略。", + "ja": "JEV は、適格なスペシャリストと照らし合わせてタスクを評価します。ローカルディスパッチルールは結果を使用します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "kentcdodds:kody", - "name": "Kody", - "owner": "kentcdodds", - "category": "search-data", - "repoUrl": "https://github.com/kentcdodds/kody", - "evidenceUrl": "https://github.com/kentcdodds/kody/blob/ed9275186dc817530dd2289e62c208ac3809391f/packages/worker/src/mcp/tools/search-jev-rerank.ts", + "id": "cognesy:instructor-php", + "name": "Instructor Php", + "owner": "cognesy", + "category": "sdk-integrations", + "repoUrl": "https://github.com/cognesy/instructor-php", + "evidenceUrl": "https://github.com/cognesy/instructor-php/blob/bb1160ce2360dcf1434788c46ee97809fe782ea3/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/kentcdodds/kody/blob/ed9275186dc817530dd2289e62c208ac3809391f/packages/worker/src/mcp/tools/search-jev-rerank.ts" + "url": "https://github.com/cognesy/instructor-php/blob/bb1160ce2360dcf1434788c46ee97809fe782ea3/README.md" }, - "language": "TypeScript", - "license": "FSL-1.1-ALv2", - "starsAtCapture": 659, + "language": "PHP", + "license": "MIT", + "starsAtCapture": 327, "summary": { - "en": "Optional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.", - "zh": "可选的二段检索：先扩大混合召回，再用 Cloudflare Workers AI 上的 `typesafe/jev` Score 重排。", - "ja": "オプションの第 2 段階の検索: ハイブリッド プールを拡大し、Workers AI typesafe/jev を使用して候補者をスコア再ランク付けします。" + "en": "A TypeSafe Decision driver within Instructor PHP’s Polyglot module.", + "zh": "Instructor PHP 的 Polyglot 模块内置 TypeSafe Decision 驱动。", + "ja": "Instructor PHP の Polyglot モジュール内の TypeSafe Decision ドライバー。" }, "decision": { - "en": "Sends a Score question per candidate, reorders and drops low scores; the model id is typesafe/jev.", - "zh": "对每个候选发 Score 问题，按分数重排并丢掉低分结果；模型 ID 为 `typesafe/jev`。", - "ja": "候補者ごとにスコアの質問を送信し、並べ替えて低いスコアを削除します。モデル ID は typesafe/jev です。" + "en": "Converts application state and typed questions into Jev requests and maps responses to PHP decision objects.", + "zh": "将业务状态和类型化问题转换为 Jev 请求，再映射为 PHP 决策响应。", + "ja": "アプリケーション状態と型付き質問を JEV リクエストへ変換し、レスポンスを PHP の意思決定オブジェクトへ割り当てます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "agentiloop:agent", - "name": "Agent", - "owner": "AgentiLoop", - "category": "safety-review", - "repoUrl": "https://github.com/AgentiLoop/Agent", - "evidenceUrl": "https://github.com/AgentiLoop/Agent/blob/078f87ceca1d1190cc73706ac8ec16442e766a27/README.md", + "id": "tax-doc-classifier", + "name": "Tax Document Classifier", + "owner": "kyotofin", + "category": "search-data", + "repoUrl": "https://github.com/kyotofin/tax-doc-classifier", + "evidenceUrl": "https://github.com/kyotofin/tax-doc-classifier/blob/6afcf701395466d7c936ec8178daf017b9d96b0c/src/backend.ts", + "language": "TypeScript", + "license": "Apache-2.0", + "starsAtCapture": 314, + "summary": { + "en": "Classifies extracted tax-document pages against a fixed IRS form catalogue.", + "zh": "把税务文档页面归入预先定义的 IRS 表格目录。", + "ja": "抽出された税務書類のページを固定 IRS フォーム カタログに基づいて分類します。" + }, + "decision": { + "en": "Returns form type, page type, and confidence while ingestion stays deterministic.", + "zh": "返回表格类型、页面类型与置信度，文档入库仍由确定性代码控制。", + "ja": "取り込みが決定的なままである間、フォーム タイプ、ページ タイプ、および信頼度を返します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/nedwize/status/2100973868324417852", + "author": "@nedwize", + "views": 223890 + } + }, + { + "id": "fhshaik:typesafe-mario", + "name": "TypeSafe Mario", + "owner": "fhshaik", + "category": "domain-tools", + "repoUrl": "https://github.com/fhshaik/typesafe-mario", + "evidenceUrl": "https://github.com/fhshaik/typesafe-mario/blob/ca22449ed187118d19326d1f54b01b6636578aa4/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/AgentiLoop/Agent/blob/078f87ceca1d1190cc73706ac8ec16442e766a27/README.md" + "url": "https://github.com/fhshaik/typesafe-mario/blob/ca22449ed187118d19326d1f54b01b6636578aa4/README.md" }, - "language": "Swift", - "license": "MIT", - "starsAtCapture": 618, + "language": "Python", + "license": "Unknown", + "starsAtCapture": 314, "summary": { - "en": "An optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.", - "zh": "原生 macOS Agent 内的可选 Jev 命令风险顾问，配有 TypeSafeKit 客户端。", - "ja": "TypeSafeKit クライアントを使用した、ネイティブ macOS エージェント内のオプションの JEV コマンド リスク アドバイザ。" + "en": "An experimental NES Mario controller that gives Jev structured emulator RAM and telemetry instead of screenshots.", + "zh": "从 NES 模拟器 RAM 和状态数据中提取环境，让 Jev 选择超级马力欧的手柄按键。", + "ja": "JEV 構造化エミュレータ RAM とスクリーンショットの代わりにテレメトリを提供する実験的な NES マリオ コントローラ。" }, "decision": { - "en": "Adds a destructive-risk judgment after local shell checks and refuses commands above the configured threshold.", - "zh": "对已通过本地规则的 Shell 命令追加破坏性判断，达到配置阈值时拒绝。", - "ja": "ローカル シェルのチェック後に破壊的リスクの判定を追加し、設定されたしきい値を超えるコマンドを拒否します。" + "en": "Reads motion, enemies, terrain and recent controls, then selects a predefined legal action.", + "zh": "读取运动、敌人、地形及近期操作状态，从预设合法操作中选一项。", + "ja": "動き、敵、地形、最近の操作を読み取り、事前に定義された法的措置を選択します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "agentjido:req_llm", - "name": "Req LLM", - "owner": "agentjido", - "category": "sdk-integrations", - "repoUrl": "https://github.com/agentjido/req_llm", - "evidenceUrl": "https://github.com/agentjido/req_llm/blob/9cb0ee7a0fea5f3520fc953911d352c93193615e/README.md", + "id": "droidrun:mobile-jev", + "name": "Mobile JEV", + "owner": "droidrun", + "category": "browser-computer-use", + "repoUrl": "https://github.com/droidrun/mobile-jev", + "evidenceUrl": "https://github.com/droidrun/mobile-jev/blob/395fc222beac4f059f9a0beb337d114a2b066e99/scripts/mobile-agent/policy.mjs#L224", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/agentjido/req_llm/blob/9cb0ee7a0fea5f3520fc953911d352c93193615e/README.md" + "url": "https://github.com/droidrun/mobile-jev/blob/395fc222beac4f059f9a0beb337d114a2b066e99/scripts/mobile-agent/policy.mjs#L224" }, - "language": "Elixir", - "license": "Apache-2.0", - "starsAtCapture": 580, + "language": "", + "license": "MIT", + "starsAtCapture": 304, "summary": { - "en": "A TypeSafe provider for calling Jev through ReqLLM’s evaluate interface in Elixir.", - "zh": "ReqLLM 的 TypeSafe provider，让 Elixir 应用通过 evaluate 接口调用 Jev。", - "ja": "Elixir の ReqLLM 評価インターフェイスから JEV を呼び出す TypeSafe プロバイダー。" + "en": "Controls an Android phone through Mobilerun, with a web studio and CLI showing Jev decisions.", + "zh": "通过 Mobilerun 控制 Android 手机，网页面板与命令行可查看 Jev 的操作过程。", + "ja": "Web スタジオと CLI で JEV の決定を表示し、Mobilerun を通じて Android スマートフォンを制御します。" }, "decision": { - "en": "Sends state and questions, normalizes answers and retains the raw provider response.", - "zh": "提交状态与判断题，将答案放入统一响应对象，并保留原始 provider 数据。", - "ja": "状態と質問を送り、回答を正規化しつつ、プロバイダーの元レスポンスも保持します。" + "en": "Chooses apps, controls and next actions from phone state; Mobilerun executes them.", + "zh": "根据手机界面选择应用、控件和下一步动作，Mobilerun 执行操作。", + "ja": "電話の状態からアプリ、コントロール、次のアクションを選択します。 Mobilerun がそれらを実行します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "bennykok:omg-dev", - "name": "Omg.dev", - "owner": "BennyKok", - "category": "browser-computer-use", - "repoUrl": "https://github.com/BennyKok/omg.dev", - "evidenceUrl": "https://github.com/BennyKok/omg.dev/blob/a00f56684a569ee417be787c148eaa9874946f2b/mobile/scripts/jev.ts", + "id": "von-open-system-one", + "name": "Von", + "owner": "wfzyx", + "category": "open-models", + "repoUrl": "https://github.com/wfzyx/von", + "evidenceUrl": "https://github.com/wfzyx/von/blob/14d09878e89b103bfbbe641f9bed02e4d72c8830/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/BennyKok/omg.dev/blob/a00f56684a569ee417be787c148eaa9874946f2b/mobile/scripts/jev.ts" + "url": "https://github.com/wfzyx/von/blob/14d09878e89b103bfbbe641f9bed02e4d72c8830/README.md" }, - "language": "TypeScript", - "license": "MIT", - "starsAtCapture": 533, + "language": "Python", + "license": "Apache-2.0", + "starsAtCapture": 297, "summary": { - "en": "An omg.dev mobile testing script can use Jev to read the accessibility tree and choose the next interaction.", - "zh": "omg.dev 的移动端测试脚本可让 Jev 读取可访问性树并选择下一步交互。", - "ja": "omg.dev モバイル テスト スクリプトは、JEV を使用してアクセシビリティ ツリーを読み取り、次のインタラクションを選択できます。" + "en": "An open, local System One decision model with a JEV-compatible interface.", + "zh": "提供 JEV 兼容接口的本地开放 System One 决策模型。", + "ja": "JEV 互換インターフェースを持つローカルのオープン System One 判断モデル。" }, "decision": { - "en": "Chooses controls and checks completion or blockage before the test runner operates the UI.", - "zh": "判断要操作的控件、步骤是否完成或是否受阻，再由测试执行器操作界面。", - "ja": "テスト ランナーが UI を操作する前に、コントロールを選択し、完了または障害をチェックします。" + "en": "Scores bounded typed choices locally without autoregressive text generation.", + "zh": "在本地为有限类型化选项评分，不做自回归文本生成。", + "ja": "自己回帰テキスト生成を行わず、限定された型付き候補をローカルで評価します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "notque:vexjoy-agent", - "name": "Vexjoy Agent", - "owner": "notque", - "category": "routing-optimization", - "repoUrl": "https://github.com/notque/vexjoy-agent", - "evidenceUrl": "https://github.com/notque/vexjoy-agent/blob/ab51ee7da567e84f72f76d73b6e7b83cec5ef060/README.md", + "id": "cobanov-awesome-jev", + "name": "Awesome JEV (cobanov)", + "owner": "cobanov", + "category": "developer-tools", + "repoUrl": "https://github.com/cobanov/awesome-jev", + "evidenceUrl": "https://github.com/cobanov/awesome-jev/blob/2c8c34a7a89499a0cec3ca7de3a23fec3ea9dc97/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/notque/vexjoy-agent/blob/ab51ee7da567e84f72f76d73b6e7b83cec5ef060/README.md" + "url": "https://github.com/cobanov/awesome-jev/blob/2c8c34a7a89499a0cec3ca7de3a23fec3ea9dc97/README.md" }, - "language": "Python", - "license": "MIT", - "starsAtCapture": 421, + "language": "Not declared", + "license": "CC0-1.0", + "starsAtCapture": 292, "summary": { - "en": "An optional Jev routing path that matches VexJoy requests to specialist Agents, skills and workflows.", - "zh": "给 VexJoy 的任务分派增加一条 Jev 路线。输入需求后，判断该选哪位专长 Agent、哪项技能和哪条工作流。", - "ja": "VexJoy リクエストを専門エージェント、スキル、ワークフローに照合するオプションの JEV ルーティング パス。" + "en": "A source-backed list of projects built with JEV / TypeSafe System One.", + "zh": "基于源码核对的 JEV / TypeSafe System One 项目精选列表。", + "ja": "JEV / TypeSafe System One で作られたプロジェクトの根拠付き一覧。" }, "decision": { - "en": "After deterministic routing guards, Jev judges the remaining candidates and required workflow components.", - "zh": "先判断是否需要路由，再从实际清单中选择候选；非法选择或调用失败交回原有流程。", - "ja": "確定的ルーティング ガードの後、JEV は残りの候補と必要なワークフロー コンポーネントを判断します。" + "en": "Highlights repositories that demonstrate concrete typed-decision integration points.", + "zh": "标出能看清类型化决策接入点的仓库。", + "ja": "型付き意思決定の具体的な接続点が見えるリポジトリを示します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "thruwire:foreman", - "name": "Foreman", - "owner": "thruwire", - "category": "developer-tools", - "repoUrl": "https://github.com/thruwire/foreman", - "evidenceUrl": "https://github.com/thruwire/foreman/blob/209182dac7a3467033fd093ab4ca47d21279984a/src/foreman/foreman/jev.py", + "id": "wy-coliney:jev-browser-use", + "name": "JEV Browser Use", + "owner": "wy-coliney", + "category": "browser-computer-use", + "repoUrl": "https://github.com/wy-coliney/jev-browser-use", + "evidenceUrl": "https://github.com/wy-coliney/jev-browser-use/blob/f14b60e0ae1ee90cd73eb6650e30a666a84c021a/skills/jev-browser-use/bridge.mjs", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/thruwire/foreman/blob/209182dac7a3467033fd093ab4ca47d21279984a/src/foreman/foreman/jev.py" + "url": "https://github.com/wy-coliney/jev-browser-use/blob/f14b60e0ae1ee90cd73eb6650e30a666a84c021a/skills/jev-browser-use/bridge.mjs" }, - "language": "Python", + "language": "JavaScript", "license": "MIT", - "starsAtCapture": 446, + "starsAtCapture": 291, "summary": { - "en": "An independent supervisor loop that reads worker diffs, logs and tests, asks Jev Nouls about stuck / off-track / verify, then applies a Python policy.", - "zh": "独立监督环读取编码工人的 diff、日志和测试，用 Jev Noul 判断卡住、跑偏、该验证，再由 Python 策略干预。", - "ja": "ワーカーの差分、ログ、テストを読み取り、スタック/オフトラック/検証について JEV Nouls に質問し、Python ポリシーを適用する独立したスーパーバイザー ループ。" + "en": "A Skill for Codex browser workflows: Jev chooses navigation, clicks, and scrolling while Codex handles text input and final checks.", + "zh": "给 Codex 浏览器工作流加一个 Skill：Jev 选导航、点击和滚动，Codex 保留文字输入与最终核验。", + "ja": "Codex ブラウザ ワークフローのスキル: JEV はナビゲーション、クリック、スクロールを選択し、Codex はテキスト入力と最終チェックを処理します。" }, "decision": { - "en": "AsyncTypeSafeClient.system_one with default jev-latest sends Noul questions for supervision.", - "zh": "`AsyncTypeSafeClient.system_one`，默认 `jev-latest`，对监督问题发 Noul。", - "ja": "デフォルトの jev-latest を使用する AsyncTypeSafeClient.system_one は、監視のために Noul の質問を送信します。" + "en": "Sends page state and permitted candidates to Jev; the existing browser connection executes the actions.", + "zh": "将页面状态与可执行候选交给 Jev，现有浏览器连接负责执行动作。", + "ja": "ページの状態と許可された候補を JEV に送信します。既存のブラウザ接続によってアクションが実行されます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "wrongstack:wrongstack", - "name": "WrongStack", - "owner": "WrongStack", + "id": "gargpratyush:jev-router", + "name": "JEV Router", + "owner": "gargpratyush", "category": "routing-optimization", - "repoUrl": "https://github.com/WrongStack/WrongStack", - "evidenceUrl": "https://github.com/WrongStack/WrongStack/blob/4cf97c0aa4f855751949ee8e99c719d06f4c26e0/README.md", + "repoUrl": "https://github.com/gargpratyush/jev-router", + "evidenceUrl": "https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/src/policy.mjs#L1-L63", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/WrongStack/WrongStack/blob/4cf97c0aa4f855751949ee8e99c719d06f4c26e0/README.md" + "url": "https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/src/policy.mjs#L1-L63" }, - "language": "TypeScript", + "language": "JavaScript", "license": "MIT", - "starsAtCapture": 329, + "starsAtCapture": 283, "summary": { - "en": "An optional Jev dispatch classifier for choosing among WrongStack specialist Agents.", - "zh": "给 WrongStack 编程 Agent 增加一个可选分派助手。遇到多个相近的专长 Agent 时，用 Jev 判断谁更适合当前任务。", - "ja": "WrongStack の専門 Agent から担当を選ぶための、任意で使える JEV ディスパッチ分類器。" + "en": "A Claude Code and CLI proxy that asks Jev to score task complexity and pick a model from the account’s available set.", + "zh": "Claude Code / CLI 代理：Jev 给任务复杂度打分，并在当前账号可用的模型里选一个，再由本地策略决定是否更换。", + "ja": "Claude Code および CLI プロキシ。JEV にタスクの複雑さをスコアリングし、アカウントの利用可能なセットからモデルを選択するよう依頼します。" }, "decision": { - "en": "Jev evaluates the task against eligible specialists; local dispatch rules use the result.", - "zh": "从候选角色中选一个，同时判断有没有任何候选真正适合；不合适时交回原有策略。", - "ja": "JEV は、適格なスペシャリストと照らし合わせてタスクを評価します。ローカルディスパッチルールは結果を使用します。" + "en": "Scores task, reasoning, and tool complexity, then chooses among the exact models the account can run; failures keep the current model.", + "zh": "三个 Score 衡量任务、推理和工具复杂度，再在可用模型上做 Choice；置信不足或 Jev 失败则保持当前模型。", + "ja": "タスク、推論、ツールの複雑さをスコアリングし、アカウントが実行できる正確なモデルの中から選択します。障害が発生しても現在のモデルが維持されます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "cognesy:instructor-php", - "name": "Instructor Php", - "owner": "cognesy", - "category": "sdk-integrations", - "repoUrl": "https://github.com/cognesy/instructor-php", - "evidenceUrl": "https://github.com/cognesy/instructor-php/blob/bb1160ce2360dcf1434788c46ee97809fe782ea3/README.md", + "id": "yonatangross:orchestkit", + "name": "Orchestkit", + "owner": "yonatangross", + "category": "developer-tools", + "repoUrl": "https://github.com/yonatangross/orchestkit", + "evidenceUrl": "https://github.com/yonatangross/orchestkit/blob/569095f35ce61a4881197dfb8117f4c3312e2bee/src/hooks/src/lib/session-category-provider.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/cognesy/instructor-php/blob/bb1160ce2360dcf1434788c46ee97809fe782ea3/README.md" + "url": "https://github.com/yonatangross/orchestkit/blob/569095f35ce61a4881197dfb8117f4c3312e2bee/src/hooks/src/lib/session-category-provider.ts" }, - "language": "PHP", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 327, + "starsAtCapture": 280, "summary": { - "en": "A TypeSafe Decision driver within Instructor PHP’s Polyglot module.", - "zh": "Instructor PHP 的 Polyglot 模块内置 TypeSafe Decision 驱动。", - "ja": "Instructor PHP の Polyglot モジュール内の TypeSafe Decision ドライバー。" + "en": "OrchestKit can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold.", + "zh": "OrchestKit 可选用 Jev 给编程会话分类，符合阈值时用结果决定会话颜色。", + "ja": "OrchestKit はオプションで JEV を使用してコーディング セッションを分類し、信頼度がしきい値を満たしたときにその色を設定できます。" }, "decision": { - "en": "Converts application state and typed questions into Jev requests and maps responses to PHP decision objects.", - "zh": "将业务状态和类型化问题转换为 Jev 请求，再映射为 PHP 决策响应。", - "ja": "アプリケーション状態と型付き質問を JEV リクエストへ変換し、レスポンスを PHP の意思決定オブジェクトへ割り当てます。" + "en": "Classifies the first task prompt and branch state by work type; local policy accepts the result or falls back.", + "zh": "将首条任务提示与分支状态分类为开发、排错等工作类型；本地规则选择采用或回退。", + "ja": "最初のタスクプロンプトとブランチ状態を作業種別ごとに分類し、ローカルポリシーが結果の採用またはフォールバックを決めます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "awlevin:typesafe-computer-use", - "name": "TypeSafe Computer Use", - "owner": "awlevin", + "id": "third-hand", + "name": "Third Hand", + "owner": "shhivv", "category": "browser-computer-use", - "repoUrl": "https://github.com/awlevin/typesafe-computer-use", - "evidenceUrl": "https://github.com/awlevin/typesafe-computer-use/blob/cc7b5066ae1a07b5e3182e8f87a9b5b6dfdcffc1/typesafe_computer_use/decide.py", + "repoUrl": "https://github.com/shhivv/third-hand", + "evidenceUrl": "https://github.com/shhivv/third-hand/blob/430394b35dbb44ff8b303bf19da29b0828d92bd2/Sources/ThirdHand/JevClient.swift", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/awlevin/typesafe-computer-use/blob/cc7b5066ae1a07b5e3182e8f87a9b5b6dfdcffc1/typesafe_computer_use/decide.py" + "url": "https://github.com/shhivv/third-hand/blob/430394b35dbb44ff8b303bf19da29b0828d92bd2/Sources/ThirdHand/JevClient.swift" }, - "language": "Python", + "language": "Swift", "license": "MIT", - "starsAtCapture": 693, + "starsAtCapture": 270, "summary": { - "en": "Builds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.", - "zh": "用 OCR 和界面状态构造候选动作，让 Jev 决定如何操作 macOS，需要写文字时再调用文本模型。", - "ja": "JEV の OCR および UI 状態から候補アクションを構築して macOS を制御し、書き込みが必要な場合にのみテキスト モデルを呼び出します。" + "en": "A Swift client stack that calls JEV while driving local computer-use style helpers.", + "zh": "Swift 客户端栈：在驱动本地 computer-use 辅助逻辑时调用 JEV。", + "ja": "ローカル Computer Use 補助を動かしつつ JEV を呼ぶ Swift クライアント。" }, "decision": { - "en": "Selects the next step from deterministically extracted controls and actions before desktop execution.", - "zh": "从确定性提取的控件与动作中选择下一步，执行器操作桌面。", - "ja": "デスクトップの実行前に、決定的に抽出されたコントロールとアクションから次のステップを選択します。" + "en": "Requests typed judgments from JEV before applying local automation actions.", + "zh": "在执行本地自动化动作前向 JEV 请求类型化判断。", + "ja": "ローカル自動化の前に JEV へ型付き判断を求めます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "jev-review", - "name": "Jev Review", - "owner": "devagrawal09", + "id": "logicrw-awesome-jev-projects", + "name": "Awesome JEV Projects", + "owner": "logicrw", "category": "developer-tools", - "repoUrl": "https://github.com/devagrawal09/jev-review", - "evidenceUrl": "https://github.com/devagrawal09/jev-review/blob/31f89602797fb7bea007f8a480bf368bf564954e/src/review/judgments.ts#L38", + "repoUrl": "https://github.com/logicrw/awesome-jev-projects", + "evidenceUrl": "https://github.com/logicrw/awesome-jev-projects/blob/d1b1b8d6c68c1754425778606d20d2cb14b09895/SKILL.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/devagrawal09/jev-review/blob/31f89602797fb7bea007f8a480bf368bf564954e/src/review/judgments.ts#L38" + "url": "https://github.com/logicrw/awesome-jev-projects/blob/d1b1b8d6c68c1754425778606d20d2cb14b09895/SKILL.md" }, - "language": "TypeScript", + "language": "JavaScript", "license": "MIT", - "starsAtCapture": 438, + "starsAtCapture": 264, "summary": { - "en": "Reviews a Git diff or a codebase in stages and displays review leads in a local dashboard.", - "zh": "分阶段检查 Git diff 或整个代码库，在本地面板里展示可复核的审查线索。", - "ja": "Git diff またはコードベースを段階的にレビューし、ローカル ダッシュボードにレビュー リードを表示します。" + "en": "A source-backed JEV ecosystem radar with plain-language discovery and GitHub sync.", + "zh": "有源码依据的 JEV 生态雷达，含白话发现页与 GitHub 同步。", + "ja": "根拠付き JEV エコシステムレーダー。平易な発見 UI と GitHub 同期付き。" }, "decision": { - "en": "Judges risk, files, evidence regions, mechanisms and severity before rule-based reviewer routing.", - "zh": "依次判断风险、文件、证据片段、问题机制和严重程度，再按规则选择审查路径。", - "ja": "ルールベースのレビュー担当者ルーティングの前に、リスク、ファイル、証拠領域、メカニズム、重大度を判断します。" + "en": "Curates which open-source JEV integrations are worth browsing by decision pattern.", + "zh": "按决策模式整理值得浏览的开源 JEV 集成。", + "ja": "意思決定パターン別に、見る価値のある OSS JEV 統合を整理します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "yonatangross:orchestkit", - "name": "Orchestkit", - "owner": "yonatangross", - "category": "developer-tools", - "repoUrl": "https://github.com/yonatangross/orchestkit", - "evidenceUrl": "https://github.com/yonatangross/orchestkit/blob/569095f35ce61a4881197dfb8117f4c3312e2bee/src/hooks/src/lib/session-category-provider.ts", + "id": "realzachi:pg-jev", + "name": "Pg JEV", + "owner": "realZachi", + "category": "search-data", + "repoUrl": "https://github.com/realZachi/pg-jev", + "evidenceUrl": "https://github.com/realZachi/pg-jev/blob/afd11fa856d7a2b831a1bfd8ee7f869ce8efcd62/sql/jev--0.2.0.sql", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/yonatangross/orchestkit/blob/569095f35ce61a4881197dfb8117f4c3312e2bee/src/hooks/src/lib/session-category-provider.ts" + "url": "https://github.com/realZachi/pg-jev/blob/afd11fa856d7a2b831a1bfd8ee7f869ce8efcd62/sql/jev--0.2.0.sql" }, - "language": "TypeScript", - "license": "MIT", - "starsAtCapture": 280, + "language": "Shell", + "license": "PostgreSQL", + "starsAtCapture": 259, "summary": { - "en": "OrchestKit can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold.", - "zh": "OrchestKit 可选用 Jev 给编程会话分类，符合阈值时用结果决定会话颜色。", - "ja": "OrchestKit はオプションで JEV を使用してコーディング セッションを分類し、信頼度がしきい値を満たしたときにその色を設定できます。" + "en": "Adds natural-language filtering, classification, and ranking of rows to PostgreSQL queries.", + "zh": "在 PostgreSQL 查询中用自然语言给数据行筛选、分类和排序。", + "ja": "PostgreSQL クエリに行の自然言語フィルタリング、分類、ランク付けを追加します。" }, "decision": { - "en": "Classifies the first task prompt and branch state by work type; local policy accepts the result or falls back.", - "zh": "将首条任务提示与分支状态分类为开发、排错等工作类型；本地规则选择采用或回退。", - "ja": "最初のタスクプロンプトとブランチ状態を作業種別ごとに分類し、ローカルポリシーが結果の採用またはフォールバックを決めます。" + "en": "Sends row content to Jev for a match decision, category, or score used by SQL conditions and ordering.", + "zh": "将行内容交给 Jev，返回是否匹配、类别或等级分数，供 SQL 条件与排序使用。", + "ja": "SQL 条件および順序付けで使用される一致判定、カテゴリ、またはスコアのために、行の内容を JEV に送信します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "fhshaik:typesafe-mario", - "name": "TypeSafe Mario", - "owner": "fhshaik", - "category": "domain-tools", - "repoUrl": "https://github.com/fhshaik/typesafe-mario", - "evidenceUrl": "https://github.com/fhshaik/typesafe-mario/blob/ca22449ed187118d19326d1f54b01b6636578aa4/README.md", - "source": { - "type": "github", - "label": "GitHub source", - "url": "https://github.com/fhshaik/typesafe-mario/blob/ca22449ed187118d19326d1f54b01b6636578aa4/README.md" - }, + "id": "jev-align", + "name": "jev-align", + "owner": "sutro-sh", + "category": "safety-review", + "repoUrl": "https://github.com/sutro-sh/jev-align", + "evidenceUrl": "https://github.com/sutro-sh/jev-align/blob/49753df924d30c0d3642b58e0b9b1e89921dc102/README.md", "language": "Python", - "license": "Unknown", - "starsAtCapture": 314, + "license": "Apache-2.0", + "starsAtCapture": 253, "summary": { - "en": "An experimental NES Mario controller that gives Jev structured emulator RAM and telemetry instead of screenshots.", - "zh": "从 NES 模拟器 RAM 和状态数据中提取环境，让 Jev 选择超级马力欧的手柄按键。", - "ja": "JEV 構造化エミュレータ RAM とスクリーンショットの代わりにテレメトリを提供する実験的な NES マリオ コントローラ。" + "en": "A CLI for calibrating Jev classifiers from human examples with GEPA.", + "zh": "用人工正反例和 GEPA 校准 JEV 分类标准的 CLI。", + "ja": "GEPA を使用して人間の例から JEV 分類器を調整するための CLI。" }, "decision": { - "en": "Reads motion, enemies, terrain and recent controls, then selects a predefined legal action.", - "zh": "读取运动、敌人、地形及近期操作状态，从预设合法操作中选一项。", - "ja": "動き、敵、地形、最近の操作を読み取り、事前に定義された法的措置を選択します。" + "en": "Optimizes the decision prompt against examples instead of relying on a generic criterion.", + "zh": "围绕明确样例优化判断标准，而不是依赖泛化提示词。", + "ja": "一般的な基準に依存するのではなく、例に基づいて決定プロンプトを最適化します。" }, "verification": "source-reviewed", - "runtimeVerified": false + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/sethkimmel3/status/2101357768640987302", + "author": "@sethkimmel3", + "views": 68757 + } }, { "id": "cequence-io:openai-scala-client", @@ -1726,6 +2160,62 @@ "verification": "source-reviewed", "runtimeVerified": false }, + { + "id": "razorback16:openjev", + "name": "Openjev", + "owner": "razorback16", + "category": "sdk-integrations", + "repoUrl": "https://github.com/razorback16/openjev", + "evidenceUrl": "https://github.com/razorback16/openjev/blob/91d5005effcf8cc0ecccaa9538ceabbb130fef59/openjev/api.py", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/razorback16/openjev/blob/91d5005effcf8cc0ecccaa9538ceabbb130fef59/openjev/api.py" + }, + "language": "Python", + "license": "Apache-2.0", + "starsAtCapture": 245, + "summary": { + "en": "An independent System One decision server compatible with Jev’s API, running an open DiffusionGemma model.", + "zh": "一个兼容 Jev System One 接口的独立决策服务，使用开源 DiffusionGemma 模型运行。", + "ja": "JEV API と互換性のある独立型 System One 意思決定サーバーで、オープンな DiffusionGemma モデルを実行します。" + }, + "decision": { + "en": "Accepts Jev-style state and Noul, Choice, and Score questions, producing probabilities with a local model.", + "zh": "接受与 Jev 相似的状态和 Noul、Choice、Score 问题，由本地模型产生概率结果。", + "ja": "JEV スタイルの状態と Noul、Choice、Score の質問を受け入れ、ローカル モデルで確率を生成します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "openjev-sglang", + "name": "OpenJEV SGLang", + "owner": "ekzhang", + "category": "open-models", + "repoUrl": "https://github.com/ekzhang/openjev-sglang", + "evidenceUrl": "https://github.com/ekzhang/openjev-sglang/blob/604664a22b2cf44c6cc499e503092ae4e3c24c03/src/openjev/__init__.py", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/ekzhang/openjev-sglang/blob/604664a22b2cf44c6cc499e503092ae4e3c24c03/src/openjev/__init__.py" + }, + "language": "Python", + "license": "Not declared", + "starsAtCapture": 245, + "summary": { + "en": "A JEV-compatible API endpoint built on open models with a prefill-only serving path.", + "zh": "基于开源模型的 JEV 兼容 API，采用 prefill-only 服务路径。", + "ja": "オープンモデル上の JEV 互換 API。prefill-only の提供経路を使います。" + }, + "decision": { + "en": "Serves System One–style probability answers from open models instead of hosted JEV.", + "zh": "用开源模型提供 System One 风格的概率答案，替代托管 JEV。", + "ja": "ホスト型 JEV の代わりに、オープンモデルで System One 風の確率回答を返します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, { "id": "monotykamary:pi-fabric", "name": "Pi Fabric", @@ -1755,253 +2245,255 @@ "runtimeVerified": false }, { - "id": "knuckles92:openwhisper", - "name": "OpenWhisper", - "owner": "Knuckles92", - "category": "interfaces", - "repoUrl": "https://github.com/Knuckles92/OpenWhisper", - "evidenceUrl": "https://github.com/Knuckles92/OpenWhisper/blob/9e83653df183096104769e302a3c907cb277c551/README.md", + "id": "openjev-verdict-2", + "name": "OpenJEV Verdict 2.0", + "owner": "Heman10x-NGU", + "category": "open-models", + "repoUrl": "https://github.com/Heman10x-NGU/openJev-verdict-2.0", + "evidenceUrl": "https://github.com/Heman10x-NGU/openJev-verdict-2.0/blob/a458733c5f43fc7f30b6e4381636cbfbf8437633/openjev/__init__.py", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/Knuckles92/OpenWhisper/blob/9e83653df183096104769e302a3c907cb277c551/README.md" + "url": "https://github.com/Heman10x-NGU/openJev-verdict-2.0/blob/a458733c5f43fc7f30b6e4381636cbfbf8437633/openjev/__init__.py" }, "language": "Python", - "license": "MIT", - "starsAtCapture": 187, + "license": "Not declared", + "starsAtCapture": 221, "summary": { - "en": "A dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.", - "zh": "语音听写与会议记录应用，可选用 Jev 检查话题变化、面向记录助手的指令和敏感文本。", - "ja": "オプションの JEV を備えたディクテーションと会議メモのアプリは、トピックの変更、メモを取る指示、機密テキストをチェックします。" + "en": "A calibrated ~151M non-autoregressive local decision engine aiming at JEV-style typed answers.", + "zh": "约 151M 的校准非自回归本地决策引擎，目标对齐类 JEV 类型化答案。", + "ja": "約 151M の校正済み非自己回帰ローカル意思決定エンジン。JEV 風の型付き回答を目指す。" }, "decision": { - "en": "Makes bounded transcript judgments for checkpoints, note-taking actions or screening before remote text cleanup.", - "zh": "对转录片段做有边界的判断，辅助触发会议检查点、记录操作或远程文本清理前的筛查。", - "ja": "チェックポイント、メモを取るアクション、またはリモート テキスト クリーンアップ前のスクリーニングについて、制限されたトランスクリプトの判断を行います。" + "en": "Produces local Noul/Choice/Score-style probabilities without calling hosted JEV.", + "zh": "不调用托管 JEV，在本地产出 Noul/Choice/Score 风格概率。", + "ja": "ホスト型 JEV を呼ばず、ローカルで Noul/Choice/Score 風の確率を出します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "realzachi:pg-jev", - "name": "Pg JEV", - "owner": "realZachi", - "category": "search-data", - "repoUrl": "https://github.com/realZachi/pg-jev", - "evidenceUrl": "https://github.com/realZachi/pg-jev/blob/afd11fa856d7a2b831a1bfd8ee7f869ce8efcd62/sql/jev--0.2.0.sql", + "id": "kitze:skillbox", + "name": "Skillbox", + "owner": "kitze", + "category": "routing-optimization", + "repoUrl": "https://github.com/kitze/skillbox", + "evidenceUrl": "https://github.com/kitze/skillbox/blob/d83ba4ecd254c8dfa6a759d1feb5141384e26a9e/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/realZachi/pg-jev/blob/afd11fa856d7a2b831a1bfd8ee7f869ce8efcd62/sql/jev--0.2.0.sql" + "url": "https://github.com/kitze/skillbox/blob/d83ba4ecd254c8dfa6a759d1feb5141384e26a9e/README.md" }, - "language": "Shell", - "license": "PostgreSQL", - "starsAtCapture": 259, + "language": "TypeScript", + "license": "MIT", + "starsAtCapture": 220, "summary": { - "en": "Adds natural-language filtering, classification, and ranking of rows to PostgreSQL queries.", - "zh": "在 PostgreSQL 查询中用自然语言给数据行筛选、分类和排序。", - "ja": "PostgreSQL クエリに行の自然言語フィルタリング、分類、ランク付けを追加します。" + "en": "A self-hosted, versioned Agent skills library with optional Jev recommendations.", + "zh": "自建一个有版本管理的 Agent 技能库，还能选配 Jev 推荐：告诉它当前任务，从你有权限使用的技能里挑更相关的。", + "ja": "オプションの JEV 推奨事項を備えた自己ホスト型のバージョン管理されたエージェント スキル ライブラリ。" }, "decision": { - "en": "Sends row content to Jev for a match decision, category, or score used by SQL conditions and ordering.", - "zh": "将行内容交给 Jev，返回是否匹配、类别或等级分数，供 SQL 条件与排序使用。", - "ja": "SQL 条件および順序付けで使用される一致判定、カテゴリ、またはスコアのために、行の内容を JEV に送信します。" + "en": "Jev scores task relevance among skills the client is allowed to access.", + "zh": "对候选技能逐项评估任务相关度，再由应用整理推荐结果。", + "ja": "JEV は、クライアントがアクセスを許可されているスキル間のタスクの関連性をスコア付けします。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "quentincody:interlinked-cli", - "name": "Interlinked CLI", - "owner": "QuentinCody", - "category": "safety-review", - "repoUrl": "https://github.com/QuentinCody/interlinked-cli", - "evidenceUrl": "https://github.com/QuentinCody/interlinked-cli/blob/207330d8131c5203ecc74e9fd4c24ba416463718/src/harness/jev/client.ts#L14", + "id": "system-one-adapter-python", + "name": "System One Adapter (Python)", + "owner": "typesafe-ai", + "category": "sdk-integrations", + "repoUrl": "https://github.com/typesafe-ai/system-one-adapter-python", + "evidenceUrl": "https://github.com/typesafe-ai/system-one-adapter-python/blob/adffc2eab300a4fa3c0e92252d4ffd6ceaa53700/src/system_one_adapter/_client.py", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/QuentinCody/interlinked-cli/blob/207330d8131c5203ecc74e9fd4c24ba416463718/src/harness/jev/client.ts#L14" + "url": "https://github.com/typesafe-ai/system-one-adapter-python/blob/adffc2eab300a4fa3c0e92252d4ffd6ceaa53700/src/system_one_adapter/_client.py" }, - "language": "", + "language": "Python", "license": "MIT", - "starsAtCapture": 178, + "starsAtCapture": 218, "summary": { - "en": "Interlinked adds optional Jev judgments and evidence checks to local coding-agent checks.", - "zh": "Interlinked 在编程 Agent 的本地检查之外，提供可选 Jev 判断与证据检查。", - "ja": "Interlinked は、任意の JEV 判断と根拠チェックをローカルのコーディング Agent 検査に追加します。" + "en": "A drop-in TypeSafeClient replacement that backs System One calls with ordinary LLM APIs.", + "zh": "可替换 TypeSafeClient 的适配器，用普通 LLM API 承接 System One 调用。", + "ja": "通常の LLM API で System One 呼び出しを受ける、TypeSafeClient 差し替えアダプタ。" }, "decision": { - "en": "Assesses inputs such as test names, documentation claims and supporting evidence.", - "zh": "评估测试名称、文档声明和对应证据等输入，给规则流程补充语义判断。", - "ja": "テスト名、文書の主張、裏付けとなる証拠などの入力を評価します。" + "en": "Maps Noul, Choice, and Score questions onto LLM providers and normalizes probabilities.", + "zh": "把 Noul / Choice / Score 问题映射到 LLM 提供方并归一化概率。", + "ja": "Noul / Choice / Score を LLM プロバイダへ写し、確率を正規化します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "gargpratyush:jev-router", - "name": "JEV Router", - "owner": "gargpratyush", - "category": "routing-optimization", - "repoUrl": "https://github.com/gargpratyush/jev-router", - "evidenceUrl": "https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/src/policy.mjs#L1-L63", + "id": "jkudish:jev-browser", + "name": "JEV Browser", + "owner": "jkudish", + "category": "browser-computer-use", + "repoUrl": "https://github.com/jkudish/jev-browser", + "evidenceUrl": "https://github.com/jkudish/jev-browser/blob/8d90c51bedbe7cd07596bfaa532ded019a31d2a8/src/navigate.ts#L1", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/src/policy.mjs#L1-L63" + "url": "https://github.com/jkudish/jev-browser/blob/8d90c51bedbe7cd07596bfaa532ded019a31d2a8/src/navigate.ts#L1" }, - "language": "JavaScript", + "language": "", "license": "MIT", - "starsAtCapture": 283, + "starsAtCapture": 209, "summary": { - "en": "A Claude Code and CLI proxy that asks Jev to score task complexity and pick a model from the account’s available set.", - "zh": "Claude Code / CLI 代理：Jev 给任务复杂度打分，并在当前账号可用的模型里选一个，再由本地策略决定是否更换。", - "ja": "Claude Code および CLI プロキシ。JEV にタスクの複雑さをスコアリングし、アカウントの利用可能なセットからモデルを選択するよう依頼します。" + "en": "Drives a browser from a task and URL, returning the final page, screenshot and action trace.", + "zh": "给定任务与网址后驱动浏览器，返回最终页面、截图和逐步操作记录。", + "ja": "タスクと URL からブラウザを起動し、最終ページ、スクリーンショット、アクション トレースを返します。" }, "decision": { - "en": "Scores task, reasoning, and tool complexity, then chooses among the exact models the account can run; failures keep the current model.", - "zh": "三个 Score 衡量任务、推理和工具复杂度，再在可用模型上做 Choice；置信不足或 Jev 失败则保持当前模型。", - "ja": "タスク、推論、ツールの複雑さをスコアリングし、アカウントが実行できる正確なモデルの中から選択します。障害が発生しても現在のモデルが維持されます。" + "en": "Chooses DOM actions and judges goal completion or stalled progress; a separate model can supply typed text.", + "zh": "从 DOM 控件选择点击、输入、选择或滚动，并判断目标是否完成、流程是否卡住。", + "ja": "DOM アクションを選択し、目標の完了または進行の停滞を判断します。別のモデルでは、入力されたテキストを提供できます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "kitze:skillbox", - "name": "Skillbox", - "owner": "kitze", - "category": "routing-optimization", - "repoUrl": "https://github.com/kitze/skillbox", - "evidenceUrl": "https://github.com/kitze/skillbox/blob/d83ba4ecd254c8dfa6a759d1feb5141384e26a9e/README.md", - "source": { - "type": "github", - "label": "GitHub source", - "url": "https://github.com/kitze/skillbox/blob/d83ba4ecd254c8dfa6a759d1feb5141384e26a9e/README.md" - }, + "id": "abide", + "name": "Abide", + "owner": "coldteadotai", + "category": "safety-review", + "repoUrl": "https://github.com/coldteadotai/abide", + "evidenceUrl": "https://github.com/coldteadotai/abide/blob/ec3352e873163b74aca1ac9cf3bd0ea69a97723a/README.md", "language": "TypeScript", "license": "MIT", - "starsAtCapture": 220, + "starsAtCapture": 199, "summary": { - "en": "A self-hosted, versioned Agent skills library with optional Jev recommendations.", - "zh": "自建一个有版本管理的 Agent 技能库，还能选配 Jev 推荐：告诉它当前任务，从你有权限使用的技能里挑更相关的。", - "ja": "オプションの JEV 推奨事項を備えた自己ホスト型のバージョン管理されたエージェント スキル ライブラリ。" + "en": "A coding-agent rule layer for constraints that ordinary linters cannot express.", + "zh": "为普通 Linter 难以表达的项目规则增加 Agent 级约束。", + "ja": "通常のリンターでは表現できない制約を扱う、コーディング Agent 向けルール層。" }, "decision": { - "en": "Jev scores task relevance among skills the client is allowed to access.", - "zh": "对候选技能逐项评估任务相关度，再由应用整理推荐结果。", - "ja": "JEV は、クライアントがアクセスを許可されているスキル間のタスクの関連性をスコア付けします。" + "en": "Scores each agent turn against semantic rules and returns targeted corrections.", + "zh": "逐轮对照语义规则评分，并把需要修正的约束返回给 Agent。", + "ja": "セマンティック ルールに対してエージェントが反抗するたびにスコアを付け、対象を絞った修正を返します。" }, "verification": "source-reviewed", - "runtimeVerified": false + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/OhansEmmanuel/status/2101034822760288452", + "author": "@OhansEmmanuel", + "views": 108458 + } }, { - "id": "droidrun:mobile-jev", - "name": "Mobile JEV", - "owner": "droidrun", - "category": "browser-computer-use", - "repoUrl": "https://github.com/droidrun/mobile-jev", - "evidenceUrl": "https://github.com/droidrun/mobile-jev/blob/395fc222beac4f059f9a0beb337d114a2b066e99/scripts/mobile-agent/policy.mjs#L224", + "id": "notra", + "name": "Notra", + "owner": "usenotra", + "category": "interfaces", + "repoUrl": "https://github.com/usenotra/notra", + "evidenceUrl": "https://github.com/usenotra/notra/blob/f792a620ef1066b34665ec84c6f55fc9ca5d9954/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/droidrun/mobile-jev/blob/395fc222beac4f059f9a0beb337d114a2b066e99/scripts/mobile-agent/policy.mjs#L224" + "url": "https://github.com/usenotra/notra/blob/f792a620ef1066b34665ec84c6f55fc9ca5d9954/README.md" }, - "language": "", - "license": "MIT", - "starsAtCapture": 304, + "language": "TypeScript", + "license": "AGPL-3.0", + "starsAtCapture": 199, "summary": { - "en": "Controls an Android phone through Mobilerun, with a web studio and CLI showing Jev decisions.", - "zh": "通过 Mobilerun 控制 Android 手机，网页面板与命令行可查看 Jev 的操作过程。", - "ja": "Web スタジオと CLI で JEV の決定を表示し、Mobilerun を通じて Android スマートフォンを制御します。" + "en": "A product that turns work artifacts into publishable content with agent skill hooks.", + "zh": "把工作产物转成可发布内容的产品，并挂接 Agent Skill。", + "ja": "作業成果を公開コンテンツに変え、Agent Skill を接続するプロダクト。" }, "decision": { - "en": "Chooses apps, controls and next actions from phone state; Mobilerun executes them.", - "zh": "根据手机界面选择应用、控件和下一步动作，Mobilerun 执行操作。", - "ja": "電話の状態からアプリ、コントロール、次のアクションを選択します。 Mobilerun がそれらを実行します。" + "en": "Uses skill-guided steps to decide what to extract and how to package content.", + "zh": "用 Skill 引导的步骤决定提取什么内容、如何打包发布。", + "ja": "Skill 案内の手順で、何を抽出しどう梱包するかを決めます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "michaelliv:runline", - "name": "Runline", - "owner": "Michaelliv", - "category": "sdk-integrations", - "repoUrl": "https://github.com/Michaelliv/runline", - "evidenceUrl": "https://github.com/Michaelliv/runline/blob/6bdddfa82cd95b6b9a07e57fd93a271ae83a0d1b/README.md", + "id": "jev-mcp", + "name": "JEV MCP", + "owner": "jkudish", + "category": "developer-tools", + "repoUrl": "https://github.com/jkudish/jev-mcp", + "evidenceUrl": "https://github.com/jkudish/jev-mcp/blob/89f88b90c3180184d56961160e7178e64c98e468/src/provider.ts#L127", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/Michaelliv/runline/blob/6bdddfa82cd95b6b9a07e57fd93a271ae83a0d1b/README.md" + "url": "https://github.com/jkudish/jev-mcp/blob/89f88b90c3180184d56961160e7178e64c98e468/src/provider.ts#L127" }, "language": "TypeScript", - "license": "Unknown", - "starsAtCapture": 162, + "license": "MIT", + "starsAtCapture": 196, "summary": { - "en": "A TypeSafe plugin exposing Jev decisions as callable actions in Runline Agent JavaScript.", - "zh": "Runline 的 TypeSafe 插件，把 Jev 判断作为 Agent JavaScript 可调用的动作。", - "ja": "Runline Agent JavaScript で呼び出し可能なアクションとして JEV 決定を公開する TypeSafe プラグイン。" + "en": "Eight MCP tools for evidence checks, content screening, search, reranking, classification, comparison and extraction.", + "zh": "给 Agent 提供核对引用、筛查内容、查找、重排、分类、比较和提取等八个 MCP 判断工具。", + "ja": "証拠チェック、コンテンツ スクリーニング、検索、再ランキング、分類、比較、抽出のための 8 つの MCP ツール。" }, "decision": { - "en": "evaluate, choice, score and noul actions submit questions and retain answers and usage.", - "zh": "evaluate、choice、score、noul 等动作提交问题并保留模型答案和用量。", - "ja": "評価、選択、スコア、および noul アクションは質問を送信し、回答と使用法を保持します。" + "en": "Uses typed questions to assess evidence support, content risk and candidate relevance.", + "zh": "用 Choice、Noul 等问题评估证据支持、内容风险和候选相关性。", + "ja": "型付きの質問 を使用して、証拠の裏付け、コンテンツのリスク、および候補者の関連性を評価します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "superagents-lab:jev-search", - "name": "JEV Search", - "owner": "superagents-lab", - "category": "search-data", - "repoUrl": "https://github.com/superagents-lab/jev-search", - "evidenceUrl": "https://github.com/superagents-lab/jev-search/blob/522868762f0637b20bf533f136e930cceb83b9f3/src/lib/typesafe.ts#L48", + "id": "typesafe-ai:typesafe-sdk-js", + "name": "TypeSafe SDK Js", + "owner": "typesafe-ai", + "category": "sdk-integrations", + "repoUrl": "https://github.com/typesafe-ai/typesafe-sdk-js", + "evidenceUrl": "https://github.com/typesafe-ai/typesafe-sdk-js/blob/66880ccded6cb642dc1809620c2b108c33730214/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/superagents-lab/jev-search/blob/522868762f0637b20bf533f136e930cceb83b9f3/src/lib/typesafe.ts#L48" + "url": "https://github.com/typesafe-ai/typesafe-sdk-js/blob/66880ccded6cb642dc1809620c2b108c33730214/README.md" }, - "language": "", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 352, + "starsAtCapture": 196, "summary": { - "en": "Searches the web with Jev choosing sources and time ranges, then ranking returned links.", - "zh": "用自然语言搜网页：Jev 选择搜索来源和时间范围，再给返回的链接排序。", - "ja": "JEV を使用して Web を検索し、ソースと時間範囲を選択し、返されたリンクをランク付けします。" + "en": "The JavaScript and TypeScript SDK published by TypeSafe, with typed Jev requests and answers.", + "zh": "TypeSafe 组织发布的 JavaScript 与 TypeScript SDK，提供 Jev 请求和回答类型。", + "ja": "TypeSafe によって公開された JavaScript および TypeScript SDK (型指定された JEV リクエストと回答を含む)。" }, "decision": { - "en": "Judges search intent, source and time settings, and relevance of individual results.", - "zh": "判断查询意图、来源与时间条件，并给各条搜索结果打相关性分数。", - "ja": "審査員は、検索の意図、ソースと時間の設定、個々の結果の関連性を判断します。" + "en": "systemOne submits state and named questions and infers answer types from the questions.", + "zh": "systemOne 提交状态与命名问题，并按问题类型推导返回答案。", + "ja": "systemOne は、状態と名前付きの質問を送信し、質問から回答タイプを推測します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "wy-coliney:jev-browser-use", - "name": "JEV Browser Use", - "owner": "wy-coliney", - "category": "browser-computer-use", - "repoUrl": "https://github.com/wy-coliney/jev-browser-use", - "evidenceUrl": "https://github.com/wy-coliney/jev-browser-use/blob/f14b60e0ae1ee90cd73eb6650e30a666a84c021a/skills/jev-browser-use/bridge.mjs", + "id": "jev-visual", + "name": "JEV Visual", + "owner": "hr98w", + "category": "open-models", + "repoUrl": "https://github.com/hr98w/jev-visual", + "evidenceUrl": "https://github.com/hr98w/jev-visual/blob/19af545f096e8db4c4dd5d47aed42d92ec252111/jev_visual/scoring.py", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/wy-coliney/jev-browser-use/blob/f14b60e0ae1ee90cd73eb6650e30a666a84c021a/skills/jev-browser-use/bridge.mjs" + "url": "https://github.com/hr98w/jev-visual/blob/19af545f096e8db4c4dd5d47aed42d92ec252111/jev_visual/scoring.py" }, - "language": "JavaScript", + "language": "Python", "license": "MIT", - "starsAtCapture": 291, + "starsAtCapture": 192, "summary": { - "en": "A Skill for Codex browser workflows: Jev chooses navigation, clicks, and scrolling while Codex handles text input and final checks.", - "zh": "给 Codex 浏览器工作流加一个 Skill：Jev 选导航、点击和滚动，Codex 保留文字输入与最终核验。", - "ja": "Codex ブラウザ ワークフローのスキル: JEV はナビゲーション、クリック、スクロールを選択し、Codex はテキスト入力と最終チェックを処理します。" + "en": "An educational JEV-like visual inference experiment on Apple Silicon with shared context scoring.", + "zh": "在 Apple Silicon 上的教学向类 JEV 视觉推理实验，共享上下文直接给候选打分。", + "ja": "Apple Silicon 上の教育向け JEV 風ビジョン推論。共有コンテキストで候補を直接採点。" }, "decision": { - "en": "Sends page state and permitted candidates to Jev; the existing browser connection executes the actions.", - "zh": "将页面状态与可执行候选交给 Jev，现有浏览器连接负责执行动作。", - "ja": "ページの状態と許可された候補を JEV に送信します。既存のブラウザ接続によってアクションが実行されます。" + "en": "Scores visual or textual candidates in one forward pass and returns calibrated probabilities.", + "zh": "一次前向为视觉或文本候选打分，并返回校准概率。", + "ja": "1 回の前向き計算で視覚／テキスト候補を採点し、校正確率を返します。" }, "verification": "source-reviewed", "runtimeVerified": false @@ -2035,169 +2527,199 @@ "runtimeVerified": false }, { - "id": "danieljvdm:effect-agent", - "name": "Effect Agent", - "owner": "danieljvdm", - "category": "sdk-integrations", - "repoUrl": "https://github.com/danieljvdm/effect-agent", - "evidenceUrl": "https://github.com/danieljvdm/effect-agent/blob/88005e497e9b627eeb16d670f278903c57601da9/README.md", + "id": "moritzkremb:jev-voice-browser", + "name": "JEV Voice Browser", + "owner": "moritzkremb", + "category": "browser-computer-use", + "repoUrl": "https://github.com/moritzkremb/jev-voice-browser", + "evidenceUrl": "https://github.com/moritzkremb/jev-voice-browser/blob/054db0f3dbf537af63a8117632d3f941ccd520e1/src/jev.js#L123", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/danieljvdm/effect-agent/blob/88005e497e9b627eeb16d670f278903c57601da9/README.md" + "url": "https://github.com/moritzkremb/jev-voice-browser/blob/054db0f3dbf537af63a8117632d3f941ccd520e1/src/jev.js#L123" }, - "language": "TypeScript", + "language": "", "license": "MIT", - "starsAtCapture": 121, + "starsAtCapture": 187, "summary": { - "en": "An Effect Agent TypeSafe decision provider for typed question sets and optional model selection.", - "zh": "Effect Agent 的 TypeSafe 决策 provider，支持类型化问题集与可选模型选择。", - "ja": "型付き質問セットと任意のモデル選択に対応する、Effect Agent 向け TypeSafe 意思決定プロバイダー。" + "en": "Controls a Playwright browser by sending incremental speech transcripts to Jev.", + "zh": "用语音控制 Playwright 浏览器，将逐步转写的口令交给 Jev 判断。", + "ja": "増分音声トランスクリプトを JEV に送信することで、Playwright ブラウザを制御します。" }, "decision": { - "en": "Jev answers probability, choice and score questions for application transitions or model selection.", - "zh": "Jev 回答概率、选择和评分问题，应用按结果执行状态转换或选择模型。", - "ja": "JEV は、アプリケーションの移行やモデルの選択に関する確率、選択、スコアの質問に答えます。" + "en": "Chooses intent, elements, URLs or verbatim spans and judges command completeness and sensitive actions.", + "zh": "选择意图、元素、网址或原文片段，并判断口令是否完整、是否涉及敏感动作。", + "ja": "インテント、要素、URL、または逐語的な範囲を選択し、コマンドの完全性と機密性の高いアクションを判断します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "jkudish:jev-browser", - "name": "JEV Browser", - "owner": "jkudish", - "category": "browser-computer-use", - "repoUrl": "https://github.com/jkudish/jev-browser", - "evidenceUrl": "https://github.com/jkudish/jev-browser/blob/8d90c51bedbe7cd07596bfaa532ded019a31d2a8/src/navigate.ts#L1", + "id": "knuckles92:openwhisper", + "name": "OpenWhisper", + "owner": "Knuckles92", + "category": "interfaces", + "repoUrl": "https://github.com/Knuckles92/OpenWhisper", + "evidenceUrl": "https://github.com/Knuckles92/OpenWhisper/blob/9e83653df183096104769e302a3c907cb277c551/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/jkudish/jev-browser/blob/8d90c51bedbe7cd07596bfaa532ded019a31d2a8/src/navigate.ts#L1" + "url": "https://github.com/Knuckles92/OpenWhisper/blob/9e83653df183096104769e302a3c907cb277c551/README.md" }, - "language": "", + "language": "Python", "license": "MIT", - "starsAtCapture": 209, + "starsAtCapture": 187, "summary": { - "en": "Drives a browser from a task and URL, returning the final page, screenshot and action trace.", - "zh": "给定任务与网址后驱动浏览器，返回最终页面、截图和逐步操作记录。", - "ja": "タスクと URL からブラウザを起動し、最終ページ、スクリーンショット、アクション トレースを返します。" + "en": "A dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.", + "zh": "语音听写与会议记录应用，可选用 Jev 检查话题变化、面向记录助手的指令和敏感文本。", + "ja": "オプションの JEV を備えたディクテーションと会議メモのアプリは、トピックの変更、メモを取る指示、機密テキストをチェックします。" }, "decision": { - "en": "Chooses DOM actions and judges goal completion or stalled progress; a separate model can supply typed text.", - "zh": "从 DOM 控件选择点击、输入、选择或滚动，并判断目标是否完成、流程是否卡住。", - "ja": "DOM アクションを選択し、目標の完了または進行の停滞を判断します。別のモデルでは、入力されたテキストを提供できます。" + "en": "Makes bounded transcript judgments for checkpoints, note-taking actions or screening before remote text cleanup.", + "zh": "对转录片段做有边界的判断，辅助触发会议检查点、记录操作或远程文本清理前的筛查。", + "ja": "チェックポイント、メモを取るアクション、またはリモート テキスト クリーンアップ前のスクリーニングについて、制限されたトランスクリプトの判断を行います。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "kitze:unclutter", - "name": "Unclutter", - "owner": "kitze", - "category": "safety-review", - "repoUrl": "https://github.com/kitze/unclutter", - "evidenceUrl": "https://github.com/kitze/unclutter/blob/9ef9beccc1e57b4e3115ae68644b8fc9c19c29f6/lib/jev.ts", + "id": "fatwang2-awesome-jev", + "name": "Awesome JEV (fatwang2)", + "owner": "fatwang2", + "category": "developer-tools", + "repoUrl": "https://github.com/fatwang2/awesome-jev", + "evidenceUrl": "https://github.com/fatwang2/awesome-jev/blob/f036095ba8203001d40be955f3486cd3e0d0a81b/.github/workflows/jev-review.yml", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/kitze/unclutter/blob/9ef9beccc1e57b4e3115ae68644b8fc9c19c29f6/lib/jev.ts" + "url": "https://github.com/fatwang2/awesome-jev/blob/f036095ba8203001d40be955f3486cd3e0d0a81b/.github/workflows/jev-review.yml" }, - "language": "TypeScript", + "language": "JavaScript", + "license": "MIT", + "starsAtCapture": 185, + "summary": { + "en": "A source-backed JEV directory plus a reusable JEV-only GitHub review workflow.", + "zh": "有源码依据的 JEV 目录，并附带可复用的纯 JEV GitHub Review 工作流。", + "ja": "根拠付き JEV ディレクトリと、再利用可能な JEV 専用 GitHub Review ワークフロー。" + }, + "decision": { + "en": "Runs JEV over pull-request signals to produce review judgments in CI.", + "zh": "在 CI 里用 JEV 阅读 PR 信号并产出审查判断。", + "ja": "CI で PR 信号を JEV に渡し、レビュー判断を出します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "jeff", + "name": "Jeff", + "owner": "logan-markewich", + "category": "open-models", + "repoUrl": "https://github.com/logan-markewich/jeff", + "evidenceUrl": "https://github.com/logan-markewich/jeff/blob/34b32f99a727c47b679adde33f4702a001e02979/README.md", + "language": "Python", "license": "MIT", - "starsAtCapture": 152, + "starsAtCapture": 183, "summary": { - "en": "A browser extension using Jev to identify ads, promotions, and subscription popups and save reusable hiding rules.", - "zh": "用 Jev 帮浏览器扩展识别网页中的广告、促销与订阅弹窗，并保存可复用的隐藏规则。", - "ja": "JEV を使用して広告、プロモーション、購読ポップアップを識別し、再利用可能な非表示ルールを保存するブラウザ拡張機能。" + "en": "A self-hosted Jev-compatible service powered by GliFormer.", + "zh": "基于 GliFormer、可自托管的 JEV 兼容服务。", + "ja": "GliFormer を利用したセルフホスト型の JEV 互換サービス。" }, "decision": { - "en": "Evaluates candidate page elements before the extension applies local hiding rules.", - "zh": "对候选页面元素做结构化判断，再由扩展应用本地隐藏规则。", - "ja": "拡張機能がローカルの非表示ルールを適用する前に、候補のページ要素を評価します。" + "en": "Preserves the decision API while running the classifier locally.", + "zh": "保留简洁的决策 API，同时在本地运行分类器。", + "ja": "分類子をローカルで実行している間、意思決定 API を保持します。" }, "verification": "source-reviewed", - "runtimeVerified": false + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/LoganMarkewich/status/2101142971223781587", + "author": "@LoganMarkewich", + "views": 29163 + } }, { - "id": "typesafe-ai:typesafe-sdk-python", - "name": "TypeSafe SDK Python", - "owner": "typesafe-ai", - "category": "sdk-integrations", - "repoUrl": "https://github.com/typesafe-ai/typesafe-sdk-python", - "evidenceUrl": "https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/src/typesafe_sdk/_core/client/sync/client.py#L206-L221", + "id": "anotiawang-awesome-jev", + "name": "Awesome JEV (AnotiaWang)", + "owner": "AnotiaWang", + "category": "developer-tools", + "repoUrl": "https://github.com/AnotiaWang/awesome-jev", + "evidenceUrl": "https://github.com/AnotiaWang/awesome-jev/blob/04e65b59a936b2fed0d40eaec71a0a11e33bb422/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/src/typesafe_sdk/_core/client/sync/client.py#L206-L221" + "url": "https://github.com/AnotiaWang/awesome-jev/blob/04e65b59a936b2fed0d40eaec71a0a11e33bb422/README.md" }, - "language": "Python", - "license": "MIT", - "starsAtCapture": 171, + "language": "", + "license": "CC0-1.0", + "starsAtCapture": 181, "summary": { - "en": "Official TypeSafe Python SDK with synchronous and asynchronous clients for Jev System One, plus question and answer types.", - "zh": "TypeSafe 官方 Python SDK，提供 Jev System One 的同步、异步客户端及问题和回答类型。", - "ja": "JEV System One の同期および非同期クライアントを備えた公式 TypeSafe Python SDK、および質問と回答のタイプ。" + "en": "A curated list of JEV applications, libraries, and System One resources.", + "zh": "JEV 应用、类库与 System One 资源精选清单。", + "ja": "JEV アプリ、ライブラリ、System One 資料のキュレーション一覧。" }, "decision": { - "en": "system_one sends context and choice, score or yes/no questions to the API, then parses answers by question name.", - "zh": "system_one 将上下文与选择、评分或是非问题提交到 API，并按问题名称解析返回的回答。", - "ja": "system_one は、コンテキストと選択肢、スコア、またははい/いいえの質問を API に送信し、質問名で回答を解析します。" + "en": "Groups ecosystem resources so builders can compare implementation patterns.", + "zh": "整理生态资源，方便开发者比较不同实现模式。", + "ja": "エコシステム資料を整理し、実装パターンを比較しやすくします。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "vinilana:jev-eval-agent", - "name": "JEV Eval Agent", - "owner": "vinilana", - "category": "domain-tools", - "repoUrl": "https://github.com/vinilana/jev-eval-agent", - "evidenceUrl": "https://github.com/vinilana/jev-eval-agent/blob/037de1120c84b4b63cdf748e2acf258ff66d7731/agent/lib/jev-router.ts#L1-L154", + "id": "decider", + "name": "Decider", + "owner": "Mapika", + "category": "open-models", + "repoUrl": "https://github.com/Mapika/decider", + "evidenceUrl": "https://github.com/Mapika/decider/blob/c4daaac28af9fea95d627015cffa2dd5a5926ee6/decider/__init__.py", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/vinilana/jev-eval-agent/blob/037de1120c84b4b63cdf748e2acf258ff66d7731/agent/lib/jev-router.ts#L1-L154" + "url": "https://github.com/Mapika/decider/blob/c4daaac28af9fea95d627015cffa2dd5a5926ee6/decider/__init__.py" }, - "language": "HTML", - "license": "Unknown", - "starsAtCapture": 99, + "language": "Python", + "license": "Apache-2.0", + "starsAtCapture": 180, "summary": { - "en": "Agent tool evaluation harness comparing standard LLM tool selection against Jev routing across 100 mocked tools.", - "zh": "智能体工具选择基准测试平台，在包含 100 个模拟工具的个人助理环境下对比大模型直接选工具与 Jev 路由的效率。", - "ja": "標準 LLM ツールの選択と 100 個のモック ツールにわたる JEV ルーティングを比較するエージェント ツール評価ハーネス。" + "en": "One-pass typed decisions with calibrated probabilities, fine-tuned from Qwen3.5-2B.", + "zh": "一次前向的类型化决策与校准概率，基于 Qwen3.5-2B 微调。", + "ja": "Qwen3.5-2B 微調整による、1 パスの型付き意思決定と校正確率。" }, "decision": { - "en": "Employs Jev for two-stage discrete pruning over tool catalogs, narrowing extensive tool lists down to relevant candidates in milliseconds.", - "zh": "利用 Jev 对上百个工具元数据进行两级离散筛选和相关性判定，把候选工具集从百级快速裁剪至少量候选。", - "ja": "ツール カタログに対する 2 段階の個別のプルーニングに JEV を採用し、広範なツール リストをミリ秒単位で関連する候補に絞り込みます。" + "en": "Returns local System One–style answers for Choice, Score, and yes/no style prompts.", + "zh": "对 Choice、Score 与是否类问题返回本地 System One 风格答案。", + "ja": "Choice / Score / 是否プロンプトにローカルな System One 風回答を返します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "rokcso:bluenoise", - "name": "Bluenoise", - "owner": "rokcso", - "category": "agent-workflows", - "repoUrl": "https://github.com/rokcso/bluenoise", - "evidenceUrl": "https://github.com/rokcso/bluenoise/blob/ef81ea7a7c3677501d6de8f9235a4d6a866b573a/entrypoints/background.ts", + "id": "quentincody:interlinked-cli", + "name": "Interlinked CLI", + "owner": "QuentinCody", + "category": "safety-review", + "repoUrl": "https://github.com/QuentinCody/interlinked-cli", + "evidenceUrl": "https://github.com/QuentinCody/interlinked-cli/blob/207330d8131c5203ecc74e9fd4c24ba416463718/src/harness/jev/client.ts#L14", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/rokcso/bluenoise/blob/ef81ea7a7c3677501d6de8f9235a4d6a866b573a/entrypoints/background.ts" + "url": "https://github.com/QuentinCody/interlinked-cli/blob/207330d8131c5203ecc74e9fd4c24ba416463718/src/harness/jev/client.ts#L14" }, - "language": "TypeScript", + "language": "", "license": "MIT", - "starsAtCapture": 90, + "starsAtCapture": 178, "summary": { - "en": "An X/Twitter filtering extension using local rules by default, with optional Jev checks for unmatched replies.", - "zh": "为 X/Twitter 过滤帖子与回复的浏览器扩展；默认用本地规则，可选择用 Jev 检查未匹配的回复。", - "ja": "デフォルトでローカル ルールを使用する X/Twitter フィルタリング拡張機能。オプションで JEV が一致しない返信をチェックします。" + "en": "Interlinked adds optional Jev judgments and evidence checks to local coding-agent checks.", + "zh": "Interlinked 在编程 Agent 的本地检查之外，提供可选 Jev 判断与证据检查。", + "ja": "Interlinked は、任意の JEV 判断と根拠チェックをローカルのコーディング Agent 検査に追加します。" }, "decision": { - "en": "When experimental AI is enabled, Jev evaluates replies missed by rules and local thresholds decide whether to hide them.", - "zh": "启用实验性 AI 后，将未命中规则的回复交给 Jev 评估，再由本地阈值决定是否隐藏。", - "ja": "実験的な AI が有効になっている場合、JEV はルールによって見逃された応答を評価し、ローカルのしきい値によってそれらを非表示にするかどうかを決定します。" + "en": "Assesses inputs such as test names, documentation claims and supporting evidence.", + "zh": "评估测试名称、文档声明和对应证据等输入，给规则流程补充语义判断。", + "ja": "テスト名、文書の主張、裏付けとなる証拠などの入力を評価します。" }, "verification": "source-reviewed", "runtimeVerified": false @@ -2231,169 +2753,169 @@ "runtimeVerified": false }, { - "id": "mrnugget:jev-shell-history", - "name": "JEV Shell History", - "owner": "mrnugget", - "category": "developer-tools", - "repoUrl": "https://github.com/mrnugget/jev-shell-history", - "evidenceUrl": "https://github.com/mrnugget/jev-shell-history/blob/4b2b75d26c0ccf5726263904514a22a8e11659ea/src/suggest.ts#L1-L196", + "id": "typesafe-ai:typesafe-sdk-python", + "name": "TypeSafe SDK Python", + "owner": "typesafe-ai", + "category": "sdk-integrations", + "repoUrl": "https://github.com/typesafe-ai/typesafe-sdk-python", + "evidenceUrl": "https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/src/typesafe_sdk/_core/client/sync/client.py#L206-L221", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/mrnugget/jev-shell-history/blob/4b2b75d26c0ccf5726263904514a22a8e11659ea/src/suggest.ts#L1-L196" + "url": "https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/src/typesafe_sdk/_core/client/sync/client.py#L206-L221" }, - "language": "TypeScript", - "license": "Unknown", - "starsAtCapture": 80, + "language": "Python", + "license": "MIT", + "starsAtCapture": 171, "summary": { - "en": "Fish-style Zsh history suggestion tool ranked by Jev, ordering candidate commands from local history based on context.", - "zh": "类似于 Fish 终端样式的 Zsh 历史命令建议工具，利用 Jev 对已有历史记录根据当前上下文进行智能打分排序。", - "ja": "JEV によってランク付けされた Fish スタイルの Zsh 履歴提案ツール。コンテキストに基づいてローカル履歴から候補コマンドを順序付けします。" + "en": "Official TypeSafe Python SDK with synchronous and asynchronous clients for Jev System One, plus question and answer types.", + "zh": "TypeSafe 官方 Python SDK，提供 Jev System One 的同步、异步客户端及问题和回答类型。", + "ja": "JEV System One の同期および非同期クライアントを備えた公式 TypeSafe Python SDK、および質問と回答のタイプ。" }, "decision": { - "en": "Packages current command input and historical candidates into a Jev request, ranking the most plausible command for inline suggestion.", - "zh": "将当前敲入的命令前缀与本地 Zsh 历史候选组装为 Jev 请求，由 Jev 评估最佳补全项，仅做行内建议而不自动执行。", - "ja": "現在のコマンド入力と過去の候補を JEV リクエストにパッケージ化し、インライン提案として最も妥当なコマンドをランク​​付けします。" + "en": "system_one sends context and choice, score or yes/no questions to the API, then parses answers by question name.", + "zh": "system_one 将上下文与选择、评分或是非问题提交到 API，并按问题名称解析返回的回答。", + "ja": "system_one は、コンテキストと選択肢、スコア、またははい/いいえの質問を API に送信し、質問名で回答を解析します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "jev-codex-router", - "name": "JEV Codex Router", - "owner": "0xNatoshi", - "category": "routing-optimization", - "repoUrl": "https://github.com/0xNatoshi/jev-codex-router", - "evidenceUrl": "https://github.com/0xNatoshi/jev-codex-router/blob/8292b519659280884627a962c826ac7721136a64/server/jev_server.py", + "id": "perch", + "name": "Perch", + "owner": "lakeday-org", + "category": "developer-tools", + "repoUrl": "https://github.com/lakeday-org/perch", + "evidenceUrl": "https://github.com/lakeday-org/perch/blob/54a38d6034264dc507e97294b82316c347fe5a5e/src/systemone.js", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/0xNatoshi/jev-codex-router/blob/8292b519659280884627a962c826ac7721136a64/server/jev_server.py" + "url": "https://github.com/lakeday-org/perch/blob/54a38d6034264dc507e97294b82316c347fe5a5e/src/systemone.js" }, - "language": "Python", + "language": "JavaScript", "license": "MIT", - "starsAtCapture": 125, + "starsAtCapture": 167, "summary": { - "en": "Uses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.", - "zh": "每轮先让 Jev 判断任务类型与难度，再由本地策略为 Codex 选模型、思考深度和速度档。", - "ja": "JEV で Codex の各ターンを分類し、ローカルルールに従ってモデル、推論強度、速度モードを選びます。" + "en": "Semantic code linting that asks JEV / System One whether findings should fire.", + "zh": "语义代码检查：用 JEV / System One 判断某条发现是否该触发。", + "ja": "発見を発火すべきかを JEV / System One に問うセマンティック lint。" }, "decision": { - "en": "Classifies task difficulty and reasoning needs before local policy selects a model configuration.", - "zh": "对当前轮次的任务层级与推理需求分类，本地规则据此选择模型配置。", - "ja": "ローカルポリシーがモデル設定を選ぶ前に、タスクの難易度と必要な推論強度を分類します。" + "en": "Scores lint candidates against project rules before reporting issues.", + "zh": "在报告问题前，按项目规则给 lint 候选项打分。", + "ja": "問題報告の前に、プロジェクト規則で lint 候補を採点します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "realzachi:typesafe-adblock", - "name": "TypeSafe Adblock", - "owner": "realZachi", - "category": "browser-computer-use", - "repoUrl": "https://github.com/realZachi/typesafe-adblock", - "evidenceUrl": "https://github.com/realZachi/typesafe-adblock/blob/7e067d243d87b7fe4d511653c0ddcd77b9beee18/src/typesafe.js", + "id": "michaelliv:runline", + "name": "Runline", + "owner": "Michaelliv", + "category": "sdk-integrations", + "repoUrl": "https://github.com/Michaelliv/runline", + "evidenceUrl": "https://github.com/Michaelliv/runline/blob/6bdddfa82cd95b6b9a07e57fd93a271ae83a0d1b/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/realZachi/typesafe-adblock/blob/7e067d243d87b7fe4d511653c0ddcd77b9beee18/src/typesafe.js" + "url": "https://github.com/Michaelliv/runline/blob/6bdddfa82cd95b6b9a07e57fd93a271ae83a0d1b/README.md" }, - "language": "JavaScript", - "license": "MIT", - "starsAtCapture": 64, + "language": "TypeScript", + "license": "Unknown", + "starsAtCapture": 162, "summary": { - "en": "An experimental Chrome extension that asks Jev whether candidate DOM elements are ads, then highlights or removes them.", - "zh": "一个实验性 Chrome 扩展，让 Jev 判断候选 DOM 元素是否是广告，再高亮或移除。", - "ja": "候補となる DOM 要素が広告であるかどうかを JEV に尋ね、それらをハイライト表示または削除する実験的な Chrome 拡張機能。" + "en": "A TypeSafe plugin exposing Jev decisions as callable actions in Runline Agent JavaScript.", + "zh": "Runline 的 TypeSafe 插件，把 Jev 判断作为 Agent JavaScript 可调用的动作。", + "ja": "Runline Agent JavaScript で呼び出し可能なアクションとして JEV 決定を公開する TypeSafe プラグイン。" }, "decision": { - "en": "Batches element text, labels, and link information into Noul questions and applies a threshold.", - "zh": "对元素文本、标签和链接等信息批量询问 Noul，按阈值应用页面操作。", - "ja": "要素のテキスト、ラベル、リンク情報を Noul の質問にバッチ処理し、しきい値を適用します。" + "en": "evaluate, choice, score and noul actions submit questions and retain answers and usage.", + "zh": "evaluate、choice、score、noul 等动作提交问题并保留模型答案和用量。", + "ja": "評価、選択、スコア、および noul アクションは質問を送信し、回答と使用法を保持します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "valentynkit:jev-skip", - "name": "JEV Skip", - "owner": "valentynkit", + "id": "compact-adviser", + "name": "Compact Adviser", + "owner": "kunchenguid", "category": "agent-workflows", - "repoUrl": "https://github.com/valentynkit/jev-skip", - "evidenceUrl": "https://github.com/valentynkit/jev-skip/blob/6837e3e0f1a48cbfc48c85415d99bcfe3eaf0628/README.md", + "repoUrl": "https://github.com/kunchenguid/compact-adviser", + "evidenceUrl": "https://github.com/kunchenguid/compact-adviser/blob/d1655faa16a22b68bff60c3d7deb0123e1e52a53/packages/codex-plugin/skills/compact-adviser/SKILL.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/valentynkit/jev-skip/blob/6837e3e0f1a48cbfc48c85415d99bcfe3eaf0628/README.md" + "url": "https://github.com/kunchenguid/compact-adviser/blob/d1655faa16a22b68bff60c3d7deb0123e1e52a53/packages/codex-plugin/skills/compact-adviser/SKILL.md" }, - "language": "", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 3, + "starsAtCapture": 157, "summary": { - "en": "A browser extension that classifies YouTube caption segments with Jev, splitting requests when the segment or token budget is exceeded, paints five categories on the seek bar, and auto-skips those painted slices over the threshold.", - "zh": "Chrome 扩展：只读字幕，把片段交给 Jev 分类（段数或 Token 预算超限就拆请求），在进度条上画出五类片段，并对达到阈值的 sponsor、self_promo、intro、outro、recap 自动跳过。", - "ja": "YouTube のキャプション セグメントを JEV で分類し、セグメントまたはトークンの予算を超過した場合にリクエストを分割し、シーク バーに 5 つのカテゴリを描画し、しきい値を超えるそれらの描画されたスライスを自動スキップするブラウザ拡張機能。" + "en": "A coding-agent skill/plugin that advises when to compact context to save tokens.", + "zh": "编码 Agent 的 Skill/插件：建议何时压缩上下文以节省 token。", + "ja": "いつコンテキストを圧縮してトークンを節約するかを助言するコーディング Agent Skill。" }, "decision": { - "en": "One Choice per caption segment among content, sponsor, intro, outro, self_promo, recap, and other. Painted categories sponsor, self_promo, intro, outro, and recap skip when probability is at or above the threshold; content and other never skip.", - "zh": "每个字幕片段一个 Choice：content、sponsor、intro、outro、self_promo、recap 或 other。绘制并跳过的是 PAINTED 五类（sponsor、self_promo、intro、outro、recap）里概率达到阈值的片段；content 和 other 不跳过。", - "ja": "コンテンツ、スポンサー、イントロ、アウトロ、自己宣伝、要約などの中からキャプション セグメントごとに 1 つの選択肢。ペイントされたカテゴリのスポンサー、セルフプロモ、イントロ、アウトロ、および要約は、確率がしきい値以上の場合にスキップされます。コンテンツなどをスキップすることはありません。" + "en": "Judges whether the session looks complete enough to compact safely.", + "zh": "判断当前会话是否已足够完整、可以安全压缩。", + "ja": "セッションが十分完了して安全に圧縮できるかを判断します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "valentynkit:jev-commit", - "name": "JEV Commit", - "owner": "valentynkit", - "category": "agent-workflows", - "repoUrl": "https://github.com/valentynkit/jev-commit", - "evidenceUrl": "https://github.com/valentynkit/jev-commit/blob/311e163b8abb9c333132155bc2e0bbfac4f36283/README.md", + "id": "djev-spark", + "name": "djev-spark", + "owner": "mmastrac", + "category": "open-models", + "repoUrl": "https://github.com/mmastrac/djev-spark", + "evidenceUrl": "https://github.com/mmastrac/djev-spark/blob/1444f3e927f83ba508e5b28a4fd4fdd9ecd0976b/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/valentynkit/jev-commit/blob/311e163b8abb9c333132155bc2e0bbfac4f36283/README.md" + "url": "https://github.com/mmastrac/djev-spark/blob/1444f3e927f83ba508e5b28a4fd4fdd9ecd0976b/README.md" }, - "language": "", - "license": "MIT", - "starsAtCapture": 8, + "language": "HTML", + "license": "Not declared", + "starsAtCapture": 152, "summary": { - "en": "A commit-msg hook that scores the message against the staged diff with one Jev request of five Nouls and warns by default. Default blocking is a local regex belt on high-precision added-line hits; the secret_shaped Noul blocks only with --strict.", - "zh": "commit-msg 钩子：一次 Jev 请求对照暂存 diff 给提交说明打五个 Noul，默认只警告。默认拦住提交的是本地正则腰带对新增行的高置信命中；secret_shaped Noul 只在 --strict 时参与拦截。", - "ja": "commit-msg フックは、5 Noul の 1 つの JEV リクエストでステージングされた差分に対してメッセージをスコアリングし、デフォルトで警告します。デフォルトのブロックは、高精度の追加行ヒットに対するローカル正規表現ベルトです。 Secret_shape の Noul ブロッ​​クは --strict でのみブロックされます。" + "en": "A DGX Spark container recipe for running DiffusionGemma NVFP4 structured decisions.", + "zh": "在 DGX Spark 上跑 DiffusionGemma NVFP4 结构化决策的容器配方。", + "ja": "DGX Spark 上で DiffusionGemma NVFP4 構造化意思決定を動かすコンテナレシピ。" }, "decision": { - "en": "Five Noul questions in one request: checkable message, hunk match, debug leftovers, unmentioned work, and credential-shaped added lines. Default blocking is the regex belt; secret_shaped participates only under --strict.", - "zh": "一次请求里五个 Noul：说明是否可核对、是否与 hunk 相符、是否留下调试代码、是否有未提及改动、新增行是否像密钥。默认拦截来自正则腰带；secret_shaped 只在 --strict 下参与拦截。", - "ja": "1 つのリクエストで 5 つの Noul 質問: チェック可能なメッセージ、ハンクの一致、デバッグの残り物、言及されていない作業、資格情報の形をした追加行。デフォルトのブロックは正規表現ベルトです。 Secret_shape は、--strict の下でのみ参加します。" + "en": "Packages local diffusion decision serving so apps can query typed outcomes on-box.", + "zh": "把本地 diffusion 决策服务打包，供应用在机器上查询类型化结果。", + "ja": "ローカル diffusion 意思決定サービスを梱包し、箱内で型付き結果を問い合わせ可能にします。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "valentynkit:jev-nvim", - "name": "Jev.nvim", - "owner": "valentynkit", - "category": "agent-workflows", - "repoUrl": "https://github.com/valentynkit/jev.nvim", - "evidenceUrl": "https://github.com/valentynkit/jev.nvim/blob/a1577b0ec874208377e5f38496577d2b8797ab11/README.md", + "id": "kitze:unclutter", + "name": "Unclutter", + "owner": "kitze", + "category": "safety-review", + "repoUrl": "https://github.com/kitze/unclutter", + "evidenceUrl": "https://github.com/kitze/unclutter/blob/9ef9beccc1e57b4e3115ae68644b8fc9c19c29f6/lib/jev.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/valentynkit/jev.nvim/blob/a1577b0ec874208377e5f38496577d2b8797ab11/README.md" + "url": "https://github.com/kitze/unclutter/blob/9ef9beccc1e57b4e3115ae68644b8fc9c19c29f6/lib/jev.ts" }, - "language": "", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 3, + "starsAtCapture": 152, "summary": { - "en": "A Neovim plugin that asks a plain-language question of every function in the buffer and lists every Jev hit in quickfix, ranked by probability.", - "zh": "Neovim 插件：用自然语言问当前 buffer，Treesitter 按函数切开，Jev 给每个函数打概率；全部命中按概率进入 quickfix。", - "ja": "Neovim プラグインは、バッファー内のすべての関数について平易な言語で質問し、クイックフィックス内のすべての JEV ヒットを確率でランク付けしてリストします。" + "en": "A browser extension using Jev to identify ads, promotions, and subscription popups and save reusable hiding rules.", + "zh": "用 Jev 帮浏览器扩展识别网页中的广告、促销与订阅弹窗，并保存可复用的隐藏规则。", + "ja": "JEV を使用して広告、プロモーション、購読ポップアップを識別し、再利用可能な非表示ルールを保存するブラウザ拡張機能。" }, "decision": { - "en": "Scores each Treesitter function against the user question, splitting across requests if the buffer does not fit. Every hit is listed in quickfix; only hits at or above the threshold get buffer marks.", - "zh": "把同一问题套到每个函数的源码上，返回概率；装不下就拆成多次请求。全部命中写入 quickfix，只有达到阈值的才打 virtual text 标记。", - "ja": "ユーザーの質問に対して各 Treesitter 関数にスコアを付け、バッファーが適合しない場合はリクエスト間で分割します。すべてのヒットはクイックフィックスにリストされます。しきい値以上のヒットのみがバッファ マークを取得します。" + "en": "Evaluates candidate page elements before the extension applies local hiding rules.", + "zh": "对候选页面元素做结构化判断，再由扩展应用本地隐藏规则。", + "ja": "拡張機能がローカルの非表示ルールを適用する前に、候補のページ要素を評価します。" }, "verification": "source-reviewed", "runtimeVerified": false @@ -2427,225 +2949,283 @@ "runtimeVerified": false }, { - "id": "romanslack:jev-drone", - "name": "JEV Drone", - "owner": "RomanSlack", - "category": "domain-tools", - "repoUrl": "https://github.com/RomanSlack/jev-drone", - "evidenceUrl": "https://github.com/RomanSlack/jev-drone/blob/cbeb53ce4f17a06ea490ae43effcdad231143610/tactics.py#L184", + "id": "hackclub:ai", + "name": "AI", + "owner": "hackclub", + "category": "sdk-integrations", + "repoUrl": "https://github.com/hackclub/ai", + "evidenceUrl": "https://github.com/hackclub/ai/blob/a76ea2cb159f707a60107935a5b2e0dbdc7455f5/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/RomanSlack/jev-drone/blob/cbeb53ce4f17a06ea490ae43effcdad231143610/tactics.py#L184" + "url": "https://github.com/hackclub/ai/blob/a76ea2cb159f707a60107935a5b2e0dbdc7455f5/README.md" }, - "language": "Python", - "license": "MIT", - "starsAtCapture": 96, + "language": "TypeScript", + "license": "Unknown", + "starsAtCapture": 133, "summary": { - "en": "A MuJoCo drone experiment deriving scene features from camera buffers for Jev tactical advice.", - "zh": "MuJoCo 无人机仿真实验：从相机缓冲区提取场景，Jev 提供战术动作建议。", - "ja": "JEV 戦術的なアドバイスのためにカメラ バッファーからシーンの特徴を導出する MuJoCo ドローン実験。" + "en": "A Jev forwarding endpoint in the Hack Club AI proxy, using its authentication, limits and usage logging.", + "zh": "Hack Club AI 代理中的 Jev 转发接口，复用已有鉴权、限额和用量记录。", + "ja": "Hack Club AI プロキシの JEV 転送エンドポイント。認証、制限、使用状況ログを使用します。" }, "decision": { - "en": "Uses range sectors, obstacle heights and target state to choose maneuvers and assess risk or target loss.", - "zh": "根据距离扇区、障碍高度与目标状态选择机动、评估风险和目标丢失状态。", - "ja": "範囲セクター、障害物の高さ、目標の状態を使用して、操縦を選択し、リスクや目標の損失を評価します。" + "en": "Forwards authorized structured requests to TypeSafe and returns answers with usage accounting.", + "zh": "把获准用户的结构化请求转发到 TypeSafe，返回模型结果并记录用量。", + "ja": "承認された構造化リクエストを TypeSafe に転送し、使用量アカウンティングを含む回答を返します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "trungdq88:youtube-sponsor-detection", - "name": "Youtube Sponsor Detection", - "owner": "trungdq88", - "category": "interfaces", - "repoUrl": "https://github.com/trungdq88/youtube-sponsor-detection", - "evidenceUrl": "https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/extension/lib/jev.js#L1-L541", + "id": "omnijev-awesome-gallery", + "name": "Awesome JEV Gallery", + "owner": "OmniJev", + "category": "developer-tools", + "repoUrl": "https://github.com/OmniJev/awesome-jev-gallery", + "evidenceUrl": "https://github.com/OmniJev/awesome-jev-gallery/blob/2b84d22ab0fb9e54098788955187feb023c40ab3/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/extension/lib/jev.js#L1-L541" + "url": "https://github.com/OmniJev/awesome-jev-gallery/blob/2b84d22ab0fb9e54098788955187feb023c40ab3/README.md" }, "language": "JavaScript", - "license": "Unknown", - "starsAtCapture": 81, + "license": "NOASSERTION", + "starsAtCapture": 131, "summary": { - "en": "YouTube extension detecting sponsored segments from live audio and transcripts using Jev, skipping promotional blocks automatically.", - "zh": "结合实时音频与字幕由 Jev 驱动的 YouTube 视频赞助广告片段检测与自动跳过扩展。", - "ja": "YouTube 拡張機能は、JEV を使用してライブ音声とトランスクリプトからスポンサー付きセグメントを検出し、プロモーション ブロックを自動的にスキップします。" + "en": "A gallery of System One papers, open reproductions, and independent evaluations.", + "zh": "汇总 System One 论文、开放复现与独立评测的 Gallery。", + "ja": "System One の論文、オープン再現、独立評価を集めたギャラリー。" }, "decision": { - "en": "Inspects transcript segments with Jev to identify sponsor reads while browser code handles playback timeline skipping.", - "zh": "提取视频字幕或音频转录切片，由 Jev 判定当前片段是否属于赞助商宣传读条，代码引擎控制时间戳与播放器快进。", - "ja": "ブラウザ コードが再生タイムラインのスキップを処理している間に、JEV を使用してトランスクリプト セグメントを検査してスポンサーの読み取りを識別します。" + "en": "Connects model implementations with research and evaluation evidence.", + "zh": "把模型实现与研究、评测证据关联起来。", + "ja": "モデル実装を研究および評価の根拠と結び付けます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "chetaslua:jevmeter", - "name": "Jevmeter", - "owner": "ChetasLua", - "category": "interfaces", - "repoUrl": "https://github.com/ChetasLua/jevmeter", - "evidenceUrl": "https://github.com/ChetasLua/jevmeter/blob/cbf8e117b5b8835e3294c3a8ee652c7dfa737a9a/jevmeter/score.py", + "id": "y0usaf:pi-jev", + "name": "Pi JEV", + "owner": "y0usaf", + "category": "safety-review", + "repoUrl": "https://github.com/y0usaf/pi-jev", + "evidenceUrl": "https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/ChetasLua/jevmeter/blob/cbf8e117b5b8835e3294c3a8ee652c7dfa737a9a/jevmeter/score.py" + "url": "https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/README.md" }, - "language": "Python", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 77, + "starsAtCapture": 131, "summary": { - "en": "Creates edited videos with score meters by asking Jev to rate transcript sentences against selected rubrics.", - "zh": "把视频转成带评分仪表的视频成片：Jev 按选定规则给字幕句子评分，再由渲染器叠加显示。", - "ja": "選択したルーブリックに対してトランスクリプト文を評価するよう JEV に依頼することで、スコア メーター付きの編集済みビデオを作成します。" + "en": "A Pi extension that flags tool risks before execution and checks output for secrets and failure types.", + "zh": "Pi 编码 Agent 扩展：执行前提示工具风险，执行后检查秘密泄露与失败类型。", + "ja": "実行前にツールのリスクにフラグを立て、出力のシークレットと障害タイプをチェックする Pi 拡張機能。" }, "decision": { - "en": "Scores transcript sentences with preset questions and scales for meters placed on the video timeline.", - "zh": "逐句读取转录文本，按预设问题和尺度返回分数，供时间轴上的仪表使用。", - "ja": "事前に設定された質問を含むトランスクリプト文をスコア化し、ビデオ タイムライン上に配置されたメーターをスケールします。" + "en": "Jev scores destructive actions, scope and output risks; configuration chooses warnings or confirmation.", + "zh": "Jev 给破坏性、越权和输出风险打分，配置决定提示还是请求确认。", + "ja": "JEV は、破壊的なアクション、範囲、および出力リスクをスコア化します。設定では警告または確認を選択します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "captaincore:captaincore", - "name": "Captaincore", - "owner": "CaptainCore", - "category": "safety-review", - "repoUrl": "https://github.com/CaptainCore/captaincore", - "evidenceUrl": "https://github.com/CaptainCore/captaincore/blob/f54e0669350707b2f4f4c67a0130fdd6574bd0b5/cmd/typesafe.go", + "id": "jev-pruner", + "name": "JEV Pruner", + "owner": "tamaratran", + "category": "agent-workflows", + "repoUrl": "https://github.com/tamaratran/jev-pruner", + "evidenceUrl": "https://github.com/tamaratran/jev-pruner/blob/47d017c34eab7690b95f075ce6f4839247c5dc0a/src/jev.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/CaptainCore/captaincore/blob/f54e0669350707b2f4f4c67a0130fdd6574bd0b5/cmd/typesafe.go" + "url": "https://github.com/tamaratran/jev-pruner/blob/47d017c34eab7690b95f075ce6f4839247c5dc0a/src/jev.ts" }, - "language": "Go", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 71, + "starsAtCapture": 130, "summary": { - "en": "Jev commands in the WordPress toolkit CaptainCore answer structured questions and prioritize malware scanner findings for review.", - "zh": "WordPress 运维工具 CaptainCore 的 Jev 命令，可询问结构化问题，并给恶意代码扫描结果排复核优先级。", - "ja": "WordPress ツールキットCaptainCore の JEV コマンドは、構造化された質問に答え、マルウェア スキャナーの検出結果に優先順位を付けてレビューします。" + "en": "A Claude Code plugin that trims long Bash output with TypeSafe JEV before the model sees it.", + "zh": "Claude Code 插件：在模型看到长 Bash 输出前，用 TypeSafe JEV 裁剪。", + "ja": "長い Bash 出力をモデルに渡す前に TypeSafe JEV で刈り込む Claude Code プラグイン。" }, "decision": { - "en": "Sends scan rules, matched snippets, and file context to Jev to assess likely true positives and suggested handling.", - "zh": "把扫描规则、命中片段与文件上下文交给 Jev，判断真阳性可能性和建议处理方式。", - "ja": "スキャン ルール、一致したスニペット、およびファイル コンテキストを JEV に送信して、真陽性の可能性と推奨される処理を評価します。" + "en": "Decides which output slices stay useful versus safe to drop under a token budget.", + "zh": "在 token 预算下判断哪些输出片段仍有用、哪些可丢弃。", + "ja": "トークン予算の下で、残すべき出力断片と捨ててよい断片を判断します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "giuliosmall:pg_typesafe", - "name": "Pg TypeSafe", - "owner": "giuliosmall", - "category": "search-data", - "repoUrl": "https://github.com/giuliosmall/pg_typesafe", - "evidenceUrl": "https://github.com/giuliosmall/pg_typesafe/blob/4b5bfc1df11b18c3f07bb10804eeb47e4508ec6a/typesafe.c", + "id": "building-with-jev-skill", + "name": "Building with JEV Skill", + "owner": "dbreunig", + "category": "developer-tools", + "repoUrl": "https://github.com/dbreunig/building-with-jev-skill", + "evidenceUrl": "https://github.com/dbreunig/building-with-jev-skill/blob/04fe3666c6b8b8abfec1271c0e581c823a181f6d/skills/jev/SKILL.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/giuliosmall/pg_typesafe/blob/4b5bfc1df11b18c3f07bb10804eeb47e4508ec6a/typesafe.c" + "url": "https://github.com/dbreunig/building-with-jev-skill/blob/04fe3666c6b8b8abfec1271c0e581c823a181f6d/skills/jev/SKILL.md" }, - "language": "C", - "license": "MIT", - "starsAtCapture": 81, + "language": "Not declared", + "license": "Not declared", + "starsAtCapture": 128, "summary": { - "en": "A pre-alpha PostgreSQL C extension for calling Jev from SQL for classification, yes/no judgments, and scoring.", - "zh": "一个预览阶段的 PostgreSQL C 扩展，让 SQL 直接调用 Jev 做分类、是非判断和评分。", - "ja": "分類、はい/いいえの判断、スコアリングのために SQL から JEV を呼び出すためのプレアルファ版の PostgreSQL C 拡張機能。" + "en": "An agent skill for writing and improving programs that call JEV / System One.", + "zh": "帮助编写与改进调用 JEV / System One 程序的 Agent Skill。", + "ja": "JEV / System One を呼ぶプログラムの作成・改善を助ける Agent Skill。" }, "decision": { - "en": "Converts SQL input into System One requests and returns answers through database functions.", - "zh": "将 SQL 输入转换为 System One 请求，并把答案返回给数据库函数。", - "ja": "SQL 入力を System One リクエストに変換し、データベース関数を通じて回答を返します。" + "en": "Advises how to frame state and questions so JEV returns usable typed answers.", + "zh": "指导如何组织 state 与 questions，让 JEV 返回可用的类型化答案。", + "ja": "使える型付き回答になるよう、state と questions の組み立て方を助言します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "featherless-ai:simple-jev", - "name": "Simple JEV", - "owner": "featherless-ai", - "category": "sdk-integrations", - "repoUrl": "https://github.com/featherless-ai/simple-jev", - "evidenceUrl": "https://github.com/featherless-ai/simple-jev/blob/0dd5396ffce671ab7c4bfc031506d8e558cf8d23/demos/jevpilot/src/simple-jev-api.js#L1-L85", + "id": "jev-codex-router", + "name": "JEV Codex Router", + "owner": "0xNatoshi", + "category": "routing-optimization", + "repoUrl": "https://github.com/0xNatoshi/jev-codex-router", + "evidenceUrl": "https://github.com/0xNatoshi/jev-codex-router/blob/8292b519659280884627a962c826ac7721136a64/server/jev_server.py", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/featherless-ai/simple-jev/blob/0dd5396ffce671ab7c4bfc031506d8e558cf8d23/demos/jevpilot/src/simple-jev-api.js#L1-L85" + "url": "https://github.com/0xNatoshi/jev-codex-router/blob/8292b519659280884627a962c826ac7721136a64/server/jev_server.py" }, "language": "Python", - "license": "Unknown", - "starsAtCapture": 428, + "license": "MIT", + "starsAtCapture": 125, "summary": { - "en": "Adapter turning open LLM endpoints into Jev-compatible classification services without training a separate classifier head.", - "zh": "将任意开源大语言模型转化为分类器与 Jev 兼容端点的适配服务，无需额外训练专用分类头。", - "ja": "専用の分類ヘッドを学習せずに、公開 LLM エンドポイントを JEV 互換の分類サービスへ変換するアダプター。" + "en": "Uses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.", + "zh": "每轮先让 Jev 判断任务类型与难度，再由本地策略为 Codex 选模型、思考深度和速度档。", + "ja": "JEV で Codex の各ターンを分類し、ローカルルールに従ってモデル、推論強度、速度モードを選びます。" }, "decision": { - "en": "Extracts log-probabilities of candidate tokens from model vocabulary logits, formatting them into standard Jev responses.", - "zh": "通过分析输入文本在模型词表中的 logits 分布，将候选项映射为标准 Jev 离散概率输出。", - "ja": "モデル語彙ロジットから候補トークンの対数確率を抽出し、標準の JEV 応答にフォーマットします。" + "en": "Classifies task difficulty and reasoning needs before local policy selects a model configuration.", + "zh": "对当前轮次的任务层级与推理需求分类，本地规则据此选择模型配置。", + "ja": "ローカルポリシーがモデル設定を選ぶ前に、タスクの難易度と必要な推論強度を分類します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "typesafe-ai:typesafe-sdk-js", - "name": "TypeSafe SDK Js", - "owner": "typesafe-ai", - "category": "sdk-integrations", - "repoUrl": "https://github.com/typesafe-ai/typesafe-sdk-js", - "evidenceUrl": "https://github.com/typesafe-ai/typesafe-sdk-js/blob/66880ccded6cb642dc1809620c2b108c33730214/README.md", + "id": "billionsbobby-jevrouter", + "name": "JevRouter", + "owner": "BillionsBobby", + "category": "routing-optimization", + "repoUrl": "https://github.com/BillionsBobby/JevRouter", + "evidenceUrl": "https://github.com/BillionsBobby/JevRouter/blob/715970774ae8070e958e83ac9b1a780b32a9184c/src/provider.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/typesafe-ai/typesafe-sdk-js/blob/66880ccded6cb642dc1809620c2b108c33730214/README.md" + "url": "https://github.com/BillionsBobby/JevRouter/blob/715970774ae8070e958e83ac9b1a780b32a9184c/src/provider.ts" }, "language": "TypeScript", "license": "MIT", - "starsAtCapture": 196, + "starsAtCapture": 125, "summary": { - "en": "The JavaScript and TypeScript SDK published by TypeSafe, with typed Jev requests and answers.", - "zh": "TypeSafe 组织发布的 JavaScript 与 TypeScript SDK，提供 Jev 请求和回答类型。", - "ja": "TypeSafe によって公開された JavaScript および TypeScript SDK (型指定された JEV リクエストと回答を含む)。" + "en": "A lightweight JEV router for models, tools, and subagents.", + "zh": "用于模型、工具与子 Agent 的轻量 JEV 路由器。", + "ja": "モデル、ツール、サブ Agent 向けの軽量 JEV ルーター。" }, "decision": { - "en": "systemOne submits state and named questions and infers answer types from the questions.", - "zh": "systemOne 提交状态与命名问题，并按问题类型推导返回答案。", - "ja": "systemOne は、状態と名前付きの質問を送信し、質問から回答タイプを推測します。" + "en": "Chooses a model, tool, or subagent from caller-supplied candidates.", + "zh": "从调用方提供的候选中选择模型、工具或子 Agent。", + "ja": "呼び出し側が与えた候補からモデル、ツール、サブ Agent を選びます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "hackclub:ai", - "name": "AI", - "owner": "hackclub", + "id": "jev-semgrep", + "name": "jev-semgrep", + "owner": "uehaj", + "category": "search-data", + "repoUrl": "https://github.com/uehaj/jev-semgrep", + "evidenceUrl": "https://github.com/uehaj/jev-semgrep/blob/ba6ef50f85d0c5d6caa4db102ee4db4a08c85dd2/README.md", + "language": "JavaScript", + "license": "Not declared", + "starsAtCapture": 122, + "summary": { + "en": "Meaning-based grep with multilingual AND, OR, NOT, and probability thresholds.", + "zh": "支持跨语言 AND、OR、NOT 与概率阈值的“按意思搜索”grep。", + "ja": "多言語の AND、OR、NOT、確率しきい値を使用した意味ベースの grep。" + }, + "decision": { + "en": "Scores whether each line satisfies a proposition, then applies grep controls locally.", + "zh": "判断每行是否满足命题，再由本地代码应用 grep 控制项。", + "ja": "各行が命題を満たすかどうかをスコアリングし、grep コントロールをローカルに適用します。" + }, + "verification": "source-reviewed", + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/uehaj/status/2101198713834381716", + "author": "@uehaj", + "views": 81889 + } + }, + { + "id": "danieljvdm:effect-agent", + "name": "Effect Agent", + "owner": "danieljvdm", "category": "sdk-integrations", - "repoUrl": "https://github.com/hackclub/ai", - "evidenceUrl": "https://github.com/hackclub/ai/blob/a76ea2cb159f707a60107935a5b2e0dbdc7455f5/README.md", + "repoUrl": "https://github.com/danieljvdm/effect-agent", + "evidenceUrl": "https://github.com/danieljvdm/effect-agent/blob/88005e497e9b627eeb16d670f278903c57601da9/README.md", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/danieljvdm/effect-agent/blob/88005e497e9b627eeb16d670f278903c57601da9/README.md" + }, + "language": "TypeScript", + "license": "MIT", + "starsAtCapture": 121, + "summary": { + "en": "An Effect Agent TypeSafe decision provider for typed question sets and optional model selection.", + "zh": "Effect Agent 的 TypeSafe 决策 provider，支持类型化问题集与可选模型选择。", + "ja": "型付き質問セットと任意のモデル選択に対応する、Effect Agent 向け TypeSafe 意思決定プロバイダー。" + }, + "decision": { + "en": "Jev answers probability, choice and score questions for application transitions or model selection.", + "zh": "Jev 回答概率、选择和评分问题，应用按结果执行状态转换或选择模型。", + "ja": "JEV は、アプリケーションの移行やモデルの選択に関する確率、選択、スコアの質問に答えます。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "devmortimer:pi-warden", + "name": "Pi Warden", + "owner": "DevMortimer", + "category": "safety-review", + "repoUrl": "https://github.com/DevMortimer/pi-warden", + "evidenceUrl": "https://github.com/DevMortimer/pi-warden/blob/e6c801679464b1a9624225114eb5fb443c27d823/src/guard.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/hackclub/ai/blob/a76ea2cb159f707a60107935a5b2e0dbdc7455f5/README.md" + "url": "https://github.com/DevMortimer/pi-warden/blob/e6c801679464b1a9624225114eb5fb443c27d823/src/guard.ts" }, "language": "TypeScript", - "license": "Unknown", - "starsAtCapture": 133, + "license": "MIT", + "starsAtCapture": 118, "summary": { - "en": "A Jev forwarding endpoint in the Hack Club AI proxy, using its authentication, limits and usage logging.", - "zh": "Hack Club AI 代理中的 Jev 转发接口，复用已有鉴权、限额和用量记录。", - "ja": "Hack Club AI プロキシの JEV 転送エンドポイント。認証、制限、使用状況ログを使用します。" + "en": "Adds checks for project rules, out-of-scope actions, repeated failures, and completion claims to Pi Agents.", + "zh": "给 Pi Agent 加项目规则、越界操作、重复失败和完成声明的检查。", + "ja": "プロジェクト ルール、範囲外のアクション、繰り返される失敗、完了要求のチェックを Pi エージェントに追加します。" }, "decision": { - "en": "Forwards authorized structured requests to TypeSafe and returns answers with usage accounting.", - "zh": "把获准用户的结构化请求转发到 TypeSafe，返回模型结果并记录用量。", - "ja": "承認された構造化リクエストを TypeSafe に転送し、使用量アカウンティングを含む回答を返します。" + "en": "Uses Jev to judge rule violations, irreversible actions, and task drift, feeding results back to the Agent.", + "zh": "用 Jev 判断写入是否违反规则、操作是否不可逆或偏离任务，并把结果反馈到 Agent。", + "ja": "JEV を使用してルール違反、取り消し不能なアクション、タスクのドリフトを判断し、結果をエージェントにフィードバックします。" }, "verification": "source-reviewed", "runtimeVerified": false @@ -2679,869 +3259,899 @@ "runtimeVerified": false }, { - "id": "moritzkremb:jev-voice-browser", - "name": "JEV Voice Browser", - "owner": "moritzkremb", - "category": "browser-computer-use", - "repoUrl": "https://github.com/moritzkremb/jev-voice-browser", - "evidenceUrl": "https://github.com/moritzkremb/jev-voice-browser/blob/054db0f3dbf537af63a8117632d3f941ccd520e1/src/jev.js#L123", + "id": "valentynkit-awesome-jev-typesafe", + "name": "Awesome JEV TypeSafe", + "owner": "valentynkit", + "category": "developer-tools", + "repoUrl": "https://github.com/valentynkit/awesome-jev-typesafe", + "evidenceUrl": "https://github.com/valentynkit/awesome-jev-typesafe/blob/7eec7360d502826b51d1c8862c9fd2d76eecf6e4/readme.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/moritzkremb/jev-voice-browser/blob/054db0f3dbf537af63a8117632d3f941ccd520e1/src/jev.js#L123" + "url": "https://github.com/valentynkit/awesome-jev-typesafe/blob/7eec7360d502826b51d1c8862c9fd2d76eecf6e4/readme.md" }, - "language": "", - "license": "MIT", - "starsAtCapture": 187, + "language": "JavaScript", + "license": "CC0-1.0", + "starsAtCapture": 115, "summary": { - "en": "Controls a Playwright browser by sending incremental speech transcripts to Jev.", - "zh": "用语音控制 Playwright 浏览器，将逐步转写的口令交给 Jev 判断。", - "ja": "増分音声トランスクリプトを JEV に送信することで、Playwright ブラウザを制御します。" + "en": "A TypeSafe JEV resource list centered on typed, confidence-aware decisions.", + "zh": "围绕类型化、置信度感知决策整理的 TypeSafe JEV 资源列表。", + "ja": "型付きで信頼度を扱う判断を中心にした TypeSafe JEV 資料一覧。" }, "decision": { - "en": "Chooses intent, elements, URLs or verbatim spans and judges command completeness and sensitive actions.", - "zh": "选择意图、元素、网址或原文片段，并判断口令是否完整、是否涉及敏感动作。", - "ja": "インテント、要素、URL、または逐語的な範囲を選択し、コマンドの完全性と機密性の高いアクションを判断します。" + "en": "Maps resources to Choice, Score, Noul, and integration patterns.", + "zh": "把资源映射到 Choice、Score、Noul 与集成模式。", + "ja": "資料を Choice、Score、Noul、連携パターンに対応付けます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "jev-mcp", - "name": "JEV MCP", - "owner": "jkudish", + "id": "hellogumbo-awesome-jev", + "name": "Awesome Jev", + "owner": "hellogumbo", "category": "developer-tools", - "repoUrl": "https://github.com/jkudish/jev-mcp", - "evidenceUrl": "https://github.com/jkudish/jev-mcp/blob/89f88b90c3180184d56961160e7178e64c98e468/src/provider.ts#L127", + "repoUrl": "https://github.com/hellogumbo/awesome-jev", + "evidenceUrl": "https://github.com/hellogumbo/awesome-jev/blob/e18fa74fa53e27395a074cf94c7a127e912fb090/data/projects.json", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/jkudish/jev-mcp/blob/89f88b90c3180184d56961160e7178e64c98e468/src/provider.ts#L127" + "url": "https://github.com/hellogumbo/awesome-jev/blob/e18fa74fa53e27395a074cf94c7a127e912fb090/data/projects.json" }, - "language": "TypeScript", - "license": "MIT", - "starsAtCapture": 196, + "language": "JavaScript", + "license": "CC0-1.0", + "starsAtCapture": 109, "summary": { - "en": "Eight MCP tools for evidence checks, content screening, search, reranking, classification, comparison and extraction.", - "zh": "给 Agent 提供核对引用、筛查内容、查找、重排、分类、比较和提取等八个 MCP 判断工具。", - "ja": "証拠チェック、コンテンツ スクリーニング、検索、再ランキング、分類、比較、抽出のための 8 つの MCP ツール。" + "en": "The source catalogue behind awesomejev.com, covering repos, integrations, demos, and research.", + "zh": "awesomejev.com 的源数据目录，覆盖仓库、集成、演示与研究。", + "ja": "awesomejev.com の元カタログで、リポジトリ、連携、デモ、研究を収録。" }, "decision": { - "en": "Uses typed questions to assess evidence support, content risk and candidate relevance.", - "zh": "用 Choice、Noul 等问题评估证据支持、内容风险和候选相关性。", - "ja": "型付きの質問 を使用して、証拠の裏付け、コンテンツのリスク、および候補者の関連性を評価します。" + "en": "Indexes the wider ecosystem while separating repositories, sites, and articles.", + "zh": "索引更广的生态，并区分仓库、网站与文章。", + "ja": "広いエコシステムを索引化し、リポジトリ、サイト、記事を区別します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "pithings:advocaat", - "name": "Advocaat", - "owner": "pithings", - "category": "sdk-integrations", - "repoUrl": "https://github.com/pithings/advocaat", - "evidenceUrl": "https://github.com/pithings/advocaat/blob/bc46287fc1102b95852a81d679c6e34a2c44f4a2/README.md", + "id": "skillranker", + "name": "Skillranker", + "owner": "Dicklesworthstone", + "category": "agent-workflows", + "repoUrl": "https://github.com/Dicklesworthstone/skillranker", + "evidenceUrl": "https://github.com/Dicklesworthstone/skillranker/blob/16743e9f9dee04850d01015d8f5c863a4ed4d0ff/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/pithings/advocaat/blob/bc46287fc1102b95852a81d679c6e34a2c44f4a2/README.md" + "url": "https://github.com/Dicklesworthstone/skillranker/blob/16743e9f9dee04850d01015d8f5c863a4ed4d0ff/README.md" }, - "language": "TypeScript", - "license": "MIT", - "starsAtCapture": 88, + "language": "Rust", + "license": "NOASSERTION", + "starsAtCapture": 107, "summary": { - "en": "A small TypeScript client for asking Jev multiple typed questions about the same data.", - "zh": "用简短的 TypeScript 调用向 Jev 提问。把同一份数据里的多个判断一次写好，直接拿到概率、选项和分数。", - "ja": "同じデータについて複数の型付き質問を JEV に送るための、小さな TypeScript クライアント。" + "en": "A Rust CLI that ranks agent skills against live session context with JEV.", + "zh": "用 JEV 根据实时会话上下文排序 Agent Skills 的 Rust CLI。", + "ja": "JEV で現在のセッション文脈に対して Agent Skills を順位付けする Rust CLI。" }, "decision": { - "en": "Combines yes/no, Choice and Score questions and maps responses to typed values.", - "zh": "将带类型的问题转成 System One 请求，并把命名答案映射回调用方。", - "ja": "Noul、Choice、Score の質問を組み合わせ、回答を型付きの値へ変換します。" + "en": "Ranks candidate skills and abstains when confidence is below policy.", + "zh": "对候选 Skill 排序，并在置信度低于策略时放弃选择。", + "ja": "候補 Skill を順位付けし、信頼度が基準未満なら選択を見送ります。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "y0usaf:pi-jev", - "name": "Pi JEV", - "owner": "y0usaf", - "category": "safety-review", - "repoUrl": "https://github.com/y0usaf/pi-jev", - "evidenceUrl": "https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/README.md", + "id": "stanley-code-jev", + "name": "Stanley Code", + "owner": "devagrawal09", + "category": "developer-tools", + "repoUrl": "https://github.com/devagrawal09/stanley-code", + "evidenceUrl": "https://github.com/devagrawal09/stanley-code/blob/fd092558ebea389c81d44f9b10e826d9a72afaa3/src/adapters/jev.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/README.md" + "url": "https://github.com/devagrawal09/stanley-code/blob/fd092558ebea389c81d44f9b10e826d9a72afaa3/src/adapters/jev.ts" }, "language": "TypeScript", "license": "MIT", - "starsAtCapture": 131, + "starsAtCapture": 106, "summary": { - "en": "A Pi extension that flags tool risks before execution and checks output for secrets and failure types.", - "zh": "Pi 编码 Agent 扩展：执行前提示工具风险，执行后检查秘密泄露与失败类型。", - "ja": "実行前にツールのリスクにフラグを立て、出力のシークレットと障害タイプをチェックする Pi 拡張機能。" + "en": "Bounded JEV workflows for coding agents with a dedicated adapter.", + "zh": "为编码 Agent 提供带专用适配器的有限 JEV 工作流。", + "ja": "専用アダプターを備えたコーディング Agent 向けの限定 JEV ワークフロー。" }, "decision": { - "en": "Jev scores destructive actions, scope and output risks; configuration chooses warnings or confirmation.", - "zh": "Jev 给破坏性、越权和输出风险打分，配置决定提示还是请求确认。", - "ja": "JEV は、破壊的なアクション、範囲、および出力リスクをスコア化します。設定では警告または確認を選択します。" + "en": "Turns review and coding checkpoints into typed JEV judgments.", + "zh": "把审查与编码检查点转成类型化 JEV 判断。", + "ja": "レビューとコーディングのチェックポイントを型付き JEV 判断に変換します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "devmortimer:pi-warden", - "name": "Pi Warden", - "owner": "DevMortimer", - "category": "safety-review", - "repoUrl": "https://github.com/DevMortimer/pi-warden", - "evidenceUrl": "https://github.com/DevMortimer/pi-warden/blob/e6c801679464b1a9624225114eb5fb443c27d823/src/guard.ts", + "id": "vinilana:jev-eval-agent", + "name": "JEV Eval Agent", + "owner": "vinilana", + "category": "domain-tools", + "repoUrl": "https://github.com/vinilana/jev-eval-agent", + "evidenceUrl": "https://github.com/vinilana/jev-eval-agent/blob/037de1120c84b4b63cdf748e2acf258ff66d7731/agent/lib/jev-router.ts#L1-L154", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/DevMortimer/pi-warden/blob/e6c801679464b1a9624225114eb5fb443c27d823/src/guard.ts" + "url": "https://github.com/vinilana/jev-eval-agent/blob/037de1120c84b4b63cdf748e2acf258ff66d7731/agent/lib/jev-router.ts#L1-L154" }, - "language": "TypeScript", + "language": "HTML", + "license": "Unknown", + "starsAtCapture": 99, + "summary": { + "en": "Agent tool evaluation harness comparing standard LLM tool selection against Jev routing across 100 mocked tools.", + "zh": "智能体工具选择基准测试平台，在包含 100 个模拟工具的个人助理环境下对比大模型直接选工具与 Jev 路由的效率。", + "ja": "標準 LLM ツールの選択と 100 個のモック ツールにわたる JEV ルーティングを比較するエージェント ツール評価ハーネス。" + }, + "decision": { + "en": "Employs Jev for two-stage discrete pruning over tool catalogs, narrowing extensive tool lists down to relevant candidates in milliseconds.", + "zh": "利用 Jev 对上百个工具元数据进行两级离散筛选和相关性判定，把候选工具集从百级快速裁剪至少量候选。", + "ja": "ツール カタログに対する 2 段階の個別のプルーニングに JEV を採用し、広範なツール リストをミリ秒単位で関連する候補に絞り込みます。" + }, + "verification": "source-reviewed", + "runtimeVerified": false + }, + { + "id": "formanator-jev", + "name": "Formanator", + "owner": "timrogers", + "category": "domain-tools", + "repoUrl": "https://github.com/timrogers/formanator", + "evidenceUrl": "https://github.com/timrogers/formanator/blob/548740edef37a4169eef163e4988e64f43a560ec/src/typesafe.rs", + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/timrogers/formanator/blob/548740edef37a4169eef163e4988e64f43a560ec/src/typesafe.rs" + }, + "language": "Rust", "license": "MIT", - "starsAtCapture": 118, + "starsAtCapture": 98, "summary": { - "en": "Adds checks for project rules, out-of-scope actions, repeated failures, and completion claims to Pi Agents.", - "zh": "给 Pi Agent 加项目规则、越界操作、重复失败和完成声明的检查。", - "ja": "プロジェクト ルール、範囲外のアクション、繰り返される失敗、完了要求のチェックを Pi エージェントに追加します。" + "en": "A CLI and MCP client for benefit claims with optional JEV receipt classification.", + "zh": "支持可选 JEV 收据分类的福利报销 CLI 与 MCP 客户端。", + "ja": "任意の JEV レシート分類を備えた福利厚生申請 CLI / MCP クライアント。" }, "decision": { - "en": "Uses Jev to judge rule violations, irreversible actions, and task drift, feeding results back to the Agent.", - "zh": "用 Jev 判断写入是否违反规则、操作是否不可逆或偏离任务，并把结果反馈到 Agent。", - "ja": "JEV を使用してルール違反、取り消し不能なアクション、タスクのドリフトを判断し、結果をエージェントにフィードバックします。" + "en": "Selects the benefit and receipt category, falling back when confidence is low.", + "zh": "选择福利与收据类别，置信度不足时回退。", + "ja": "福利厚生とレシートのカテゴリを選び、信頼度が低い場合はフォールバックします。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "razorback16:openjev", - "name": "Openjev", - "owner": "razorback16", - "category": "sdk-integrations", - "repoUrl": "https://github.com/razorback16/openjev", - "evidenceUrl": "https://github.com/razorback16/openjev/blob/91d5005effcf8cc0ecccaa9538ceabbb130fef59/openjev/api.py", + "id": "romanslack:jev-drone", + "name": "JEV Drone", + "owner": "RomanSlack", + "category": "domain-tools", + "repoUrl": "https://github.com/RomanSlack/jev-drone", + "evidenceUrl": "https://github.com/RomanSlack/jev-drone/blob/cbeb53ce4f17a06ea490ae43effcdad231143610/tactics.py#L184", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/razorback16/openjev/blob/91d5005effcf8cc0ecccaa9538ceabbb130fef59/openjev/api.py" + "url": "https://github.com/RomanSlack/jev-drone/blob/cbeb53ce4f17a06ea490ae43effcdad231143610/tactics.py#L184" }, "language": "Python", - "license": "Apache-2.0", - "starsAtCapture": 245, + "license": "MIT", + "starsAtCapture": 96, "summary": { - "en": "An independent System One decision server compatible with Jev’s API, running an open DiffusionGemma model.", - "zh": "一个兼容 Jev System One 接口的独立决策服务，使用开源 DiffusionGemma 模型运行。", - "ja": "JEV API と互換性のある独立型 System One 意思決定サーバーで、オープンな DiffusionGemma モデルを実行します。" + "en": "A MuJoCo drone experiment deriving scene features from camera buffers for Jev tactical advice.", + "zh": "MuJoCo 无人机仿真实验：从相机缓冲区提取场景，Jev 提供战术动作建议。", + "ja": "JEV 戦術的なアドバイスのためにカメラ バッファーからシーンの特徴を導出する MuJoCo ドローン実験。" }, "decision": { - "en": "Accepts Jev-style state and Noul, Choice, and Score questions, producing probabilities with a local model.", - "zh": "接受与 Jev 相似的状态和 Noul、Choice、Score 问题，由本地模型产生概率结果。", - "ja": "JEV スタイルの状態と Noul、Choice、Score の質問を受け入れ、ローカル モデルで確率を生成します。" + "en": "Uses range sectors, obstacle heights and target state to choose maneuvers and assess risk or target loss.", + "zh": "根据距离扇区、障碍高度与目标状态选择机动、评估风险和目标丢失状态。", + "ja": "範囲セクター、障害物の高さ、目標の状態を使用して、操縦を選択し、リスクや目標の損失を評価します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "openwork", - "name": "Openwork", - "owner": "different-ai", - "category": "agent-workflows", - "repoUrl": "https://github.com/different-ai/openwork", - "evidenceUrl": "https://github.com/different-ai/openwork/blob/80c74d2160034fa1738fc6be78dd24ddfeccfc59/.github/scripts/jev-test-coverage-review.mjs", + "id": "reflex-open-decision-model", + "name": "Reflex", + "owner": "kshetrajna12", + "category": "open-models", + "repoUrl": "https://github.com/kshetrajna12/reflex", + "evidenceUrl": "https://github.com/kshetrajna12/reflex/blob/e21b3b23afdfeee7021a6604fa38f57e7ff5187f/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/different-ai/openwork/blob/80c74d2160034fa1738fc6be78dd24ddfeccfc59/.github/scripts/jev-test-coverage-review.mjs" + "url": "https://github.com/kshetrajna12/reflex/blob/e21b3b23afdfeee7021a6604fa38f57e7ff5187f/README.md" }, - "language": "TypeScript", - "license": "Not declared", - "starsAtCapture": 23682, + "language": "Python", + "license": "MIT", + "starsAtCapture": 91, "summary": { - "en": "An open-source cowork-style agent workspace that can run JEV-backed reviews inside CI and skill workflows.", - "zh": "开源的 cowork 风格 Agent 工作区，可在 CI 与 Skill 流程里跑 JEV 驱动的审查。", - "ja": "CI と Skill ワークフローで JEV レビューを実行できる、オープンソースの cowork 風エージェント作業空間。" + "en": "A small open decision model that recreates the JEV/System One interface on Qwen.", + "zh": "在 Qwen 上复现 JEV/System One 接口的小型开放决策模型。", + "ja": "Qwen 上で JEV/System One インターフェースを再現する小型オープン判断モデル。" }, "decision": { - "en": "Scores or gates test-coverage and review findings before merging agent-produced changes.", - "zh": "在合并 Agent 产出前，对测试覆盖与审查结论做评分或门禁。", - "ja": "エージェント成果をマージする前に、テストカバレッジやレビュー結果を評価・ゲートします。" + "en": "Returns calibrated probabilities for state plus typed questions.", + "zh": "对状态与类型化问题返回校准概率。", + "ja": "状態と型付き質問に対して較正済み確率を返します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "vercel-eve", - "name": "Eve", - "owner": "vercel", + "id": "rokcso:bluenoise", + "name": "Bluenoise", + "owner": "rokcso", "category": "agent-workflows", - "repoUrl": "https://github.com/vercel/eve", - "evidenceUrl": "https://github.com/vercel/eve/blob/d004e6d47e9d25d0380c24b5a47b65a18f8b2784/README.md", + "repoUrl": "https://github.com/rokcso/bluenoise", + "evidenceUrl": "https://github.com/rokcso/bluenoise/blob/ef81ea7a7c3677501d6de8f9235a4d6a866b573a/entrypoints/background.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/vercel/eve/blob/d004e6d47e9d25d0380c24b5a47b65a18f8b2784/README.md" + "url": "https://github.com/rokcso/bluenoise/blob/ef81ea7a7c3677501d6de8f9235a4d6a866b573a/entrypoints/background.ts" }, "language": "TypeScript", - "license": "Apache-2.0", - "starsAtCapture": 5291, + "license": "MIT", + "starsAtCapture": 90, "summary": { - "en": "Vercel’s open agent framework for packaging skills, evals, and tool-using workflows.", - "zh": "Vercel 开源的 Agent 框架，用于打包 Skill、评测与带工具的工作流。", - "ja": "Skill・評価・ツール付きワークフローをまとめる Vercel のオープンなエージェント枠組み。" + "en": "An X/Twitter filtering extension using local rules by default, with optional Jev checks for unmatched replies.", + "zh": "为 X/Twitter 过滤帖子与回复的浏览器扩展；默认用本地规则，可选择用 Jev 检查未匹配的回复。", + "ja": "デフォルトでローカル ルールを使用する X/Twitter フィルタリング拡張機能。オプションで JEV が一致しない返信をチェックします。" }, "decision": { - "en": "Structures agent runs so later steps can apply typed judgments before acting.", - "zh": "把 Agent 运行结构化，便于后续步骤在行动前做类型化判断。", - "ja": "エージェント実行を構造化し、行動前に型付き判断を差し込めるようにします。" + "en": "When experimental AI is enabled, Jev evaluates replies missed by rules and local thresholds decide whether to hide them.", + "zh": "启用实验性 AI 后，将未命中规则的回复交给 Jev 评估，再由本地阈值决定是否隐藏。", + "ja": "実験的な AI が有効になっている場合、JEV はルールによって見逃された応答を評価し、ローカルのしきい値によってそれらを非表示にするかどうかを決定します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "vercel-ai-cli", - "name": "AI CLI", - "owner": "vercel-labs", - "category": "developer-tools", - "repoUrl": "https://github.com/vercel-labs/ai-cli", - "evidenceUrl": "https://github.com/vercel-labs/ai-cli/blob/6a0ed5d04ea60ee536029d469499b82898d1b214/skills/ai-cli/SKILL.md", + "id": "dasheng-jev-reading", + "name": "Dasheng", + "owner": "wquguru", + "category": "domain-tools", + "repoUrl": "https://github.com/wquguru/dasheng", + "evidenceUrl": "https://github.com/wquguru/dasheng/blob/1bacff4a075527e6c02da242a72d117e7cb3286b/lib/jev.js", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/vercel-labs/ai-cli/blob/6a0ed5d04ea60ee536029d469499b82898d1b214/skills/ai-cli/SKILL.md" + "url": "https://github.com/wquguru/dasheng/blob/1bacff4a075527e6c02da242a72d117e7cb3286b/lib/jev.js" }, - "language": "TypeScript", - "license": "Not declared", - "starsAtCapture": 808, + "language": "JavaScript", + "license": "Unknown", + "starsAtCapture": 90, "summary": { - "en": "A terminal generator CLI that ships with an agent skill for creating content from the command line.", - "zh": "终端生成 CLI，并附带可从命令行创作内容的 Agent Skill。", - "ja": "ターミナルからコンテンツ生成するための Agent Skill 付き CLI。" + "en": "A reading-practice app that combines streaming ASR with per-word JEV judgments.", + "zh": "把流式 ASR 与 JEV 逐词判断结合的朗读练习应用。", + "ja": "ストリーミング ASR と単語ごとの JEV 判断を組み合わせた音読練習アプリ。" }, "decision": { - "en": "Chooses generation steps and skill instructions before local CLI execution.", - "zh": "在本地 CLI 执行前选择生成步骤与 Skill 说明。", - "ja": "ローカル CLI 実行前に生成手順と Skill 指示を選びます。" + "en": "Judges word matches, error classes, and sentence similarity from aligned text.", + "zh": "根据对齐文本判断单词匹配、错误类别与句子相似度。", + "ja": "整列済みテキストから単語一致、誤り分類、文の類似度を判断します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "typesafe-skills", - "name": "TypeSafe Skills", - "owner": "typesafe-ai", - "category": "developer-tools", - "repoUrl": "https://github.com/typesafe-ai/skills", - "evidenceUrl": "https://github.com/typesafe-ai/skills/blob/65a39f393687675ce170e6094757de20370365b9/skills/typesafe-ai/SKILL.md", + "id": "pithings:advocaat", + "name": "Advocaat", + "owner": "pithings", + "category": "sdk-integrations", + "repoUrl": "https://github.com/pithings/advocaat", + "evidenceUrl": "https://github.com/pithings/advocaat/blob/bc46287fc1102b95852a81d679c6e34a2c44f4a2/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/typesafe-ai/skills/blob/65a39f393687675ce170e6094757de20370365b9/skills/typesafe-ai/SKILL.md" + "url": "https://github.com/pithings/advocaat/blob/bc46287fc1102b95852a81d679c6e34a2c44f4a2/README.md" }, - "language": "Not declared", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 1388, - "summary": { - "en": "Official agent skills for building against TypeSafe’s System One / JEV API.", - "zh": "面向 TypeSafe System One / JEV API 的官方 Agent Skill 集合。", - "ja": "TypeSafe の System One / JEV API 向け公式 Agent Skill 集。" + "starsAtCapture": 88, + "summary": { + "en": "A small TypeScript client for asking Jev multiple typed questions about the same data.", + "zh": "用简短的 TypeScript 调用向 Jev 提问。把同一份数据里的多个判断一次写好，直接拿到概率、选项和分数。", + "ja": "同じデータについて複数の型付き質問を JEV に送るための、小さな TypeScript クライアント。" }, "decision": { - "en": "Guides agents to frame Noul, Choice, and Score questions against System One.", - "zh": "指导 Agent 把 Noul / Choice / Score 问题正确提交给 System One。", - "ja": "エージェントが Noul / Choice / Score を System One に正しく投げるよう導きます。" + "en": "Combines yes/no, Choice and Score questions and maps responses to typed values.", + "zh": "将带类型的问题转成 System One 请求，并把命名答案映射回调用方。", + "ja": "Noul、Choice、Score の質問を組み合わせ、回答を型付きの値へ変換します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "awesome-jev-by-typesafe", - "name": "Awesome JEV by TypeSafe", - "owner": "Anil-matcha", - "category": "developer-tools", - "repoUrl": "https://github.com/Anil-matcha/awesome-jev-by-typesafe", - "evidenceUrl": "https://github.com/Anil-matcha/awesome-jev-by-typesafe/blob/0f4a1eadcdd70f4fc1cf8eadcf72794dfe416095/docs/jev-use-case-playbook.md", + "id": "supercov-jev-quality", + "name": "Supercov", + "owner": "supercorp-ai", + "category": "safety-review", + "repoUrl": "https://github.com/supercorp-ai/supercov", + "evidenceUrl": "https://github.com/supercorp-ai/supercov/blob/55f5ce93a239829c224b89e6749991310be91ea4/crates/supercov-cli/src/quality.rs", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/Anil-matcha/awesome-jev-by-typesafe/blob/0f4a1eadcdd70f4fc1cf8eadcf72794dfe416095/docs/jev-use-case-playbook.md" + "url": "https://github.com/supercorp-ai/supercov/blob/55f5ce93a239829c224b89e6749991310be91ea4/crates/supercov-cli/src/quality.rs" }, - "language": "Python", + "language": "Rust", "license": "MIT", - "starsAtCapture": 742, + "starsAtCapture": 85, "summary": { - "en": "An evidence-backed playbook of JEV use cases, patterns, prompts, and starter code.", - "zh": "有证据支撑的 JEV 用例、模式、提示词与起步代码手册。", - "ja": "根拠付きの JEV ユースケース・パターン・プロンプト・スターター集。" + "en": "A code-quality and coverage tool that uses JEV for bounded quality checks.", + "zh": "使用 JEV 做有限质量检查的代码质量与覆盖率工具。", + "ja": "JEV で限定的な品質チェックを行うコード品質・カバレッジツール。" }, "decision": { - "en": "Helps builders pick which typed decision pattern fits a product workflow.", - "zh": "帮助开发者判断哪种类型化决策模式适合自己的产品流程。", - "ja": "どの型付き意思決定パターンが製品フローに合うかを選ぶ助けになります。" + "en": "Scores whether generated tests and coverage changes meet configured quality criteria.", + "zh": "判断生成测试与覆盖率变化是否满足配置的质量标准。", + "ja": "生成テストとカバレッジ変更が設定した品質基準を満たすか評価します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "smithers", - "name": "Smithers", - "owner": "smithersai", - "category": "agent-workflows", - "repoUrl": "https://github.com/smithersai/smithers", - "evidenceUrl": "https://github.com/smithersai/smithers/blob/394ada6a3fb815b4b62cfc7bc2242e238d42ff44/apps/server/src/jev.ts", + "id": "daseinlabs-open-jev", + "name": "Open JEV", + "owner": "daseinlabs", + "category": "open-models", + "repoUrl": "https://github.com/daseinlabs/open-jev", + "evidenceUrl": "https://github.com/daseinlabs/open-jev/blob/8a4fbdf712e78c5ef45509a16aacb81facdd79be/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/smithersai/smithers/blob/394ada6a3fb815b4b62cfc7bc2242e238d42ff44/apps/server/src/jev.ts" + "url": "https://github.com/daseinlabs/open-jev/blob/8a4fbdf712e78c5ef45509a16aacb81facdd79be/README.md" }, - "language": "TypeScript", - "license": "MIT", - "starsAtCapture": 418, + "language": "Python", + "license": "Unknown", + "starsAtCapture": 82, "summary": { - "en": "An agentic TypeScript workflow framework with a first-class JEV classify path.", - "zh": "以 TypeScript 配置定义工作流的 Agent 框架，内置 JEV 分类路径。", - "ja": "TypeScript 設定でワークフローを定義し、JEV 分類パスを持つエージェント枠組み。" + "en": "An open JEV-style implementation with custom fine-tuning support.", + "zh": "支持自定义微调的开放 JEV 风格实现。", + "ja": "カスタム微調整に対応するオープンな JEV 形式の実装。" }, "decision": { - "en": "Classifies workflow steps or review verdicts through a dedicated JEV relay.", - "zh": "通过专用 JEV 中继对工作流步骤或审查结论做分类。", - "ja": "専用の JEV 中継でワークフロー手順やレビュー判定を分類します。" + "en": "Runs bounded decision questions on a locally trainable model.", + "zh": "用可本地训练的模型处理有限决策问题。", + "ja": "ローカル学習可能なモデルで限定的な判断質問を処理します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "jev-cu", - "name": "Jev CU", - "owner": "Sac-Y", - "category": "browser-computer-use", - "repoUrl": "https://github.com/Sac-Y/Jev-cu", - "evidenceUrl": "https://github.com/Sac-Y/Jev-cu/blob/38fb31de7dfe6209bbe6e04057c00c6e885ba577/scripts/jev-decide.mjs", + "id": "giuliosmall:pg_typesafe", + "name": "Pg TypeSafe", + "owner": "giuliosmall", + "category": "search-data", + "repoUrl": "https://github.com/giuliosmall/pg_typesafe", + "evidenceUrl": "https://github.com/giuliosmall/pg_typesafe/blob/4b5bfc1df11b18c3f07bb10804eeb47e4508ec6a/typesafe.c", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/Sac-Y/Jev-cu/blob/38fb31de7dfe6209bbe6e04057c00c6e885ba577/scripts/jev-decide.mjs" + "url": "https://github.com/giuliosmall/pg_typesafe/blob/4b5bfc1df11b18c3f07bb10804eeb47e4508ec6a/typesafe.c" }, - "language": "JavaScript", - "license": "Not declared", - "starsAtCapture": 519, + "language": "C", + "license": "MIT", + "starsAtCapture": 81, "summary": { - "en": "Computer-use helpers that call JEV to decide the next UI action.", - "zh": "用 JEV 决定下一步界面动作的 Computer Use 辅助工具。", - "ja": "次の UI 操作を JEV に決めさせる Computer Use 補助ツール。" + "en": "A pre-alpha PostgreSQL C extension for calling Jev from SQL for classification, yes/no judgments, and scoring.", + "zh": "一个预览阶段的 PostgreSQL C 扩展，让 SQL 直接调用 Jev 做分类、是非判断和评分。", + "ja": "分類、はい/いいえの判断、スコアリングのために SQL から JEV を呼び出すためのプレアルファ版の PostgreSQL C 拡張機能。" }, "decision": { - "en": "Picks a bounded next action from observed UI state before local execution.", - "zh": "根据观察到的界面状态，在本地执行前选出有限下一步动作。", - "ja": "観測した UI 状態から、ローカル実行前に有限の次アクションを選びます。" + "en": "Converts SQL input into System One requests and returns answers through database functions.", + "zh": "将 SQL 输入转换为 System One 请求，并把答案返回给数据库函数。", + "ja": "SQL 入力を System One リクエストに変換し、データベース関数を通じて回答を返します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "splash", - "name": "Splash", - "owner": "incoai", - "category": "open-models", - "repoUrl": "https://github.com/incoai/splash", - "evidenceUrl": "https://github.com/incoai/splash/blob/f53d5ab543a7accdc332c060fd594a693f33f529/README.md", + "id": "trungdq88:youtube-sponsor-detection", + "name": "Youtube Sponsor Detection", + "owner": "trungdq88", + "category": "interfaces", + "repoUrl": "https://github.com/trungdq88/youtube-sponsor-detection", + "evidenceUrl": "https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/extension/lib/jev.js#L1-L541", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/incoai/splash/blob/f53d5ab543a7accdc332c060fd594a693f33f529/README.md" + "url": "https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/extension/lib/jev.js#L1-L541" }, - "language": "Python", - "license": "Apache-2.0", - "starsAtCapture": 506, + "language": "JavaScript", + "license": "Unknown", + "starsAtCapture": 81, "summary": { - "en": "A local Apple Silicon inference engine oriented around decision-style models.", - "zh": "面向决策类模型的本地 Apple Silicon 推理引擎。", - "ja": "意思決定系モデル向けの Apple Silicon ローカル推論エンジン。" + "en": "YouTube extension detecting sponsored segments from live audio and transcripts using Jev, skipping promotional blocks automatically.", + "zh": "结合实时音频与字幕由 Jev 驱动的 YouTube 视频赞助广告片段检测与自动跳过扩展。", + "ja": "YouTube 拡張機能は、JEV を使用してライブ音声とトランスクリプトからスポンサー付きセグメントを検出し、プロモーション ブロックを自動的にスキップします。" }, "decision": { - "en": "Runs local inference so apps can obtain typed judgments without a remote JEV hop.", - "zh": "在本地完成推理，让应用无需远程 JEV 也能拿到类型化判断。", - "ja": "ローカル推論で型付き判断を返し、遠隔 JEV なしでも使えるようにします。" + "en": "Inspects transcript segments with Jev to identify sponsor reads while browser code handles playback timeline skipping.", + "zh": "提取视频字幕或音频转录切片，由 Jev 判定当前片段是否属于赞助商宣传读条，代码引擎控制时间戳与播放器快进。", + "ja": "ブラウザ コードが再生タイムラインのスキップを処理している間に、JEV を使用してトランスクリプト セグメントを検査してスポンサーの読み取りを識別します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "awesome-typesafe", - "name": "Awesome TypeSafe", - "owner": "AbdelStark", + "id": "mrnugget:jev-shell-history", + "name": "JEV Shell History", + "owner": "mrnugget", "category": "developer-tools", - "repoUrl": "https://github.com/AbdelStark/awesome-typesafe", - "evidenceUrl": "https://github.com/AbdelStark/awesome-typesafe/blob/d44dc0a1e26d41bc7f543d39b4b62ae5cb9f13c8/README.md", + "repoUrl": "https://github.com/mrnugget/jev-shell-history", + "evidenceUrl": "https://github.com/mrnugget/jev-shell-history/blob/4b2b75d26c0ccf5726263904514a22a8e11659ea/src/suggest.ts#L1-L196", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/AbdelStark/awesome-typesafe/blob/d44dc0a1e26d41bc7f543d39b4b62ae5cb9f13c8/README.md" + "url": "https://github.com/mrnugget/jev-shell-history/blob/4b2b75d26c0ccf5726263904514a22a8e11659ea/src/suggest.ts#L1-L196" }, - "language": "CSS", - "license": "MIT", - "starsAtCapture": 414, + "language": "TypeScript", + "license": "Unknown", + "starsAtCapture": 80, "summary": { - "en": "A curated list of official and community resources for TypeSafe, System One, and JEV.", - "zh": "TypeSafe、System One 与 JEV 的官方与社区资源精选列表。", - "ja": "TypeSafe・System One・JEV の公式／コミュニティ資源をまとめたキュレーション一覧。" + "en": "Fish-style Zsh history suggestion tool ranked by Jev, ordering candidate commands from local history based on context.", + "zh": "类似于 Fish 终端样式的 Zsh 历史命令建议工具，利用 Jev 对已有历史记录根据当前上下文进行智能打分排序。", + "ja": "JEV によってランク付けされた Fish スタイルの Zsh 履歴提案ツール。コンテキストに基づいてローカル履歴から候補コマンドを順序付けします。" }, "decision": { - "en": "Surfaces which projects and docs are worth opening when building with System One.", - "zh": "帮你判断做 System One 时该先打开哪些项目与文档。", - "ja": "System One 開発時に開くべきプロジェクト／ドキュメントを示します。" + "en": "Packages current command input and historical candidates into a Jev request, ranking the most plausible command for inline suggestion.", + "zh": "将当前敲入的命令前缀与本地 Zsh 历史候选组装为 Jev 请求，由 Jev 评估最佳补全项，仅做行内建议而不自动执行。", + "ja": "現在のコマンド入力と過去の候補を JEV リクエストにパッケージ化し、インライン提案として最も妥当なコマンドをランク​​付けします。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "cobanov-awesome-jev", - "name": "Awesome JEV (cobanov)", - "owner": "cobanov", - "category": "developer-tools", - "repoUrl": "https://github.com/cobanov/awesome-jev", - "evidenceUrl": "https://github.com/cobanov/awesome-jev/blob/2c8c34a7a89499a0cec3ca7de3a23fec3ea9dc97/README.md", + "id": "savka777-jev-use", + "name": "JEV Use", + "owner": "savka777", + "category": "browser-computer-use", + "repoUrl": "https://github.com/savka777/jev-use", + "evidenceUrl": "https://github.com/savka777/jev-use/blob/8907f85354addfa3d2b78f6a462087e4c73310b8/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/cobanov/awesome-jev/blob/2c8c34a7a89499a0cec3ca7de3a23fec3ea9dc97/README.md" + "url": "https://github.com/savka777/jev-use/blob/8907f85354addfa3d2b78f6a462087e4c73310b8/README.md" }, - "language": "Not declared", - "license": "CC0-1.0", - "starsAtCapture": 292, + "language": "Swift", + "license": "MIT", + "starsAtCapture": 79, "summary": { - "en": "A source-backed list of projects built with JEV / TypeSafe System One.", - "zh": "基于源码核对的 JEV / TypeSafe System One 项目精选列表。", - "ja": "JEV / TypeSafe System One で作られたプロジェクトの根拠付き一覧。" + "en": "A macOS computer-use harness that drives Accessibility controls without a vision model.", + "zh": "无需视觉模型、通过无障碍控件操作 macOS 的 Computer Use 工具。", + "ja": "視覚モデルなしで Accessibility 要素を操作する macOS Computer Use ツール。" }, "decision": { - "en": "Highlights repositories that demonstrate concrete typed-decision integration points.", - "zh": "标出能看清类型化决策接入点的仓库。", - "ja": "型付き意思決定の具体的な接続点が見えるリポジトリを示します。" + "en": "Chooses a visible accessibility element and the next allowed action.", + "zh": "选择可见无障碍元素与下一步允许的动作。", + "ja": "表示中の Accessibility 要素と次の許可済み操作を選びます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "openjev-sglang", - "name": "OpenJEV SGLang", - "owner": "ekzhang", - "category": "open-models", - "repoUrl": "https://github.com/ekzhang/openjev-sglang", - "evidenceUrl": "https://github.com/ekzhang/openjev-sglang/blob/604664a22b2cf44c6cc499e503092ae4e3c24c03/src/openjev/__init__.py", - "source": { - "type": "github", - "label": "GitHub source", - "url": "https://github.com/ekzhang/openjev-sglang/blob/604664a22b2cf44c6cc499e503092ae4e3c24c03/src/openjev/__init__.py" - }, - "language": "Python", - "license": "Not declared", - "starsAtCapture": 245, + "id": "jev-gateway", + "name": "jev-gateway", + "owner": "vinilana", + "category": "agent-workflows", + "repoUrl": "https://github.com/vinilana/jev-gateway", + "evidenceUrl": "https://github.com/vinilana/jev-gateway/blob/9463952bf118773fb955427d2725a98f76546233/README.md", + "language": "TypeScript", + "license": "MIT", + "starsAtCapture": 79, "summary": { - "en": "A JEV-compatible API endpoint built on open models with a prefill-only serving path.", - "zh": "基于开源模型的 JEV 兼容 API，采用 prefill-only 服务路径。", - "ja": "オープンモデル上の JEV 互換 API。prefill-only の提供経路を使います。" + "en": "A gateway for inserting Jev decisions into Claude Code and Codex tool flows.", + "zh": "把 JEV 判断接入 Claude Code 与 Codex 工具流程的网关。", + "ja": "JEV 決定を Claude Code および Codex ツール フローに挿入するためのゲートウェイ。" }, "decision": { - "en": "Serves System One–style probability answers from open models instead of hosted JEV.", - "zh": "用开源模型提供 System One 风格的概率答案，替代托管 JEV。", - "ja": "ホスト型 JEV の代わりに、オープンモデルで System One 風の確率回答を返します。" + "en": "Delegates bounded tool-choice judgments while the coding agent owns the broader task.", + "zh": "把有限的工具选择判断分离出来，完整任务仍由编码 Agent 负责。", + "ja": "コーディングエージェントがより広範なタスクを所有する一方で、限定されたツール選択の判断を委任します。" }, "verification": "source-reviewed", - "runtimeVerified": false + "runtimeVerified": false, + "source": { + "type": "x", + "label": "Original X case", + "url": "https://x.com/oviniciuslana/status/2101057880640127230", + "author": "@oviniciuslana", + "views": 53439 + } }, { - "id": "notra", - "name": "Notra", - "owner": "usenotra", + "id": "chetaslua:jevmeter", + "name": "Jevmeter", + "owner": "ChetasLua", "category": "interfaces", - "repoUrl": "https://github.com/usenotra/notra", - "evidenceUrl": "https://github.com/usenotra/notra/blob/f792a620ef1066b34665ec84c6f55fc9ca5d9954/README.md", + "repoUrl": "https://github.com/ChetasLua/jevmeter", + "evidenceUrl": "https://github.com/ChetasLua/jevmeter/blob/cbf8e117b5b8835e3294c3a8ee652c7dfa737a9a/jevmeter/score.py", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/usenotra/notra/blob/f792a620ef1066b34665ec84c6f55fc9ca5d9954/README.md" + "url": "https://github.com/ChetasLua/jevmeter/blob/cbf8e117b5b8835e3294c3a8ee652c7dfa737a9a/jevmeter/score.py" }, - "language": "TypeScript", - "license": "AGPL-3.0", - "starsAtCapture": 199, + "language": "Python", + "license": "MIT", + "starsAtCapture": 77, "summary": { - "en": "A product that turns work artifacts into publishable content with agent skill hooks.", - "zh": "把工作产物转成可发布内容的产品，并挂接 Agent Skill。", - "ja": "作業成果を公開コンテンツに変え、Agent Skill を接続するプロダクト。" + "en": "Creates edited videos with score meters by asking Jev to rate transcript sentences against selected rubrics.", + "zh": "把视频转成带评分仪表的视频成片：Jev 按选定规则给字幕句子评分，再由渲染器叠加显示。", + "ja": "選択したルーブリックに対してトランスクリプト文を評価するよう JEV に依頼することで、スコア メーター付きの編集済みビデオを作成します。" }, "decision": { - "en": "Uses skill-guided steps to decide what to extract and how to package content.", - "zh": "用 Skill 引导的步骤决定提取什么内容、如何打包发布。", - "ja": "Skill 案内の手順で、何を抽出しどう梱包するかを決めます。" + "en": "Scores transcript sentences with preset questions and scales for meters placed on the video timeline.", + "zh": "逐句读取转录文本，按预设问题和尺度返回分数，供时间轴上的仪表使用。", + "ja": "事前に設定された質問を含むトランスクリプト文をスコア化し、ビデオ タイムライン上に配置されたメーターをスケールします。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "system-one-adapter-python", - "name": "System One Adapter (Python)", - "owner": "typesafe-ai", - "category": "sdk-integrations", - "repoUrl": "https://github.com/typesafe-ai/system-one-adapter-python", - "evidenceUrl": "https://github.com/typesafe-ai/system-one-adapter-python/blob/adffc2eab300a4fa3c0e92252d4ffd6ceaa53700/src/system_one_adapter/_client.py", + "id": "captaincore:captaincore", + "name": "Captaincore", + "owner": "CaptainCore", + "category": "safety-review", + "repoUrl": "https://github.com/CaptainCore/captaincore", + "evidenceUrl": "https://github.com/CaptainCore/captaincore/blob/f54e0669350707b2f4f4c67a0130fdd6574bd0b5/cmd/typesafe.go", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/typesafe-ai/system-one-adapter-python/blob/adffc2eab300a4fa3c0e92252d4ffd6ceaa53700/src/system_one_adapter/_client.py" + "url": "https://github.com/CaptainCore/captaincore/blob/f54e0669350707b2f4f4c67a0130fdd6574bd0b5/cmd/typesafe.go" }, - "language": "Python", + "language": "Go", "license": "MIT", - "starsAtCapture": 218, - "summary": { - "en": "A drop-in TypeSafeClient replacement that backs System One calls with ordinary LLM APIs.", - "zh": "可替换 TypeSafeClient 的适配器，用普通 LLM API 承接 System One 调用。", - "ja": "通常の LLM API で System One 呼び出しを受ける、TypeSafeClient 差し替えアダプタ。" + "starsAtCapture": 71, + "summary": { + "en": "Jev commands in the WordPress toolkit CaptainCore answer structured questions and prioritize malware scanner findings for review.", + "zh": "WordPress 运维工具 CaptainCore 的 Jev 命令，可询问结构化问题，并给恶意代码扫描结果排复核优先级。", + "ja": "WordPress ツールキットCaptainCore の JEV コマンドは、構造化された質問に答え、マルウェア スキャナーの検出結果に優先順位を付けてレビューします。" }, "decision": { - "en": "Maps Noul, Choice, and Score questions onto LLM providers and normalizes probabilities.", - "zh": "把 Noul / Choice / Score 问题映射到 LLM 提供方并归一化概率。", - "ja": "Noul / Choice / Score を LLM プロバイダへ写し、確率を正規化します。" + "en": "Sends scan rules, matched snippets, and file context to Jev to assess likely true positives and suggested handling.", + "zh": "把扫描规则、命中片段与文件上下文交给 Jev，判断真阳性可能性和建议处理方式。", + "ja": "スキャン ルール、一致したスニペット、およびファイル コンテキストを JEV に送信して、真陽性の可能性と推奨される処理を評価します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "fatwang2-awesome-jev", - "name": "Awesome JEV (fatwang2)", - "owner": "fatwang2", - "category": "developer-tools", - "repoUrl": "https://github.com/fatwang2/awesome-jev", - "evidenceUrl": "https://github.com/fatwang2/awesome-jev/blob/f036095ba8203001d40be955f3486cd3e0d0a81b/.github/workflows/jev-review.yml", + "id": "jev-chat", + "name": "JEV Chat", + "owner": "w3cj", + "category": "interfaces", + "repoUrl": "https://github.com/w3cj/jev-chat", + "evidenceUrl": "https://github.com/w3cj/jev-chat/blob/e543aba8c21b57a28a748ef41966502130f0f69e/apps/server/src/jev/pools.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/fatwang2/awesome-jev/blob/f036095ba8203001d40be955f3486cd3e0d0a81b/.github/workflows/jev-review.yml" + "url": "https://github.com/w3cj/jev-chat/blob/e543aba8c21b57a28a748ef41966502130f0f69e/apps/server/src/jev/pools.ts" }, - "language": "JavaScript", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 185, + "starsAtCapture": 71, "summary": { - "en": "A source-backed JEV directory plus a reusable JEV-only GitHub review workflow.", - "zh": "有源码依据的 JEV 目录，并附带可复用的纯 JEV GitHub Review 工作流。", - "ja": "根拠付き JEV ディレクトリと、再利用可能な JEV 専用 GitHub Review ワークフロー。" + "en": "A tool-using chat interface where JEV chooses only from code-supplied reply and tool options.", + "zh": "由 JEV 仅从代码提供的回复与工具选项中选择的工具型聊天界面。", + "ja": "JEV がコード提供の返答・ツール候補だけから選ぶツール利用チャット。" }, "decision": { - "en": "Runs JEV over pull-request signals to produce review judgments in CI.", - "zh": "在 CI 里用 JEV 阅读 PR 信号并产出审查判断。", - "ja": "CI で PR 信号を JEV に渡し、レビュー判断を出します。" + "en": "Selects tools, arguments, and reply fragments from bounded pools.", + "zh": "从有限候选池中选择工具、参数与回复片段。", + "ja": "限定プールからツール、引数、返答断片を選びます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "perch", - "name": "Perch", - "owner": "lakeday-org", - "category": "developer-tools", - "repoUrl": "https://github.com/lakeday-org/perch", - "evidenceUrl": "https://github.com/lakeday-org/perch/blob/54a38d6034264dc507e97294b82316c347fe5a5e/src/systemone.js", + "id": "grok-bot-jev", + "name": "Grok Bot JEV", + "owner": "Bodila51", + "category": "routing-optimization", + "repoUrl": "https://github.com/Bodila51/grok-bot-jev", + "evidenceUrl": "https://github.com/Bodila51/grok-bot-jev/blob/1583e09928c138aeac0aa89818c67ea41f08e807/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/lakeday-org/perch/blob/54a38d6034264dc507e97294b82316c347fe5a5e/src/systemone.js" + "url": "https://github.com/Bodila51/grok-bot-jev/blob/1583e09928c138aeac0aa89818c67ea41f08e807/README.md" }, - "language": "JavaScript", + "language": "Python", "license": "MIT", - "starsAtCapture": 167, + "starsAtCapture": 68, "summary": { - "en": "Semantic code linting that asks JEV / System One whether findings should fire.", - "zh": "语义代码检查：用 JEV / System One 判断某条发现是否该触发。", - "ja": "発見を発火すべきかを JEV / System One に問うセマンティック lint。" + "en": "A JEV decision layer for Grok Bot with usage gates and skill templates.", + "zh": "为 Grok Bot 提供用量闸门与 Skill 模板的 JEV 决策层。", + "ja": "使用量ゲートと Skill テンプレートを備えた Grok Bot 向け JEV 判断レイヤー。" }, "decision": { - "en": "Scores lint candidates against project rules before reporting issues.", - "zh": "在报告问题前，按项目规则给 lint 候选项打分。", - "ja": "問題報告の前に、プロジェクト規則で lint 候補を採点します。" + "en": "Routes bounded bot decisions before more expensive generation runs.", + "zh": "在更昂贵的生成前路由有限的 Bot 决策。", + "ja": "高価な生成前に限定された Bot 判断をルーティングします。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "jev-visual", - "name": "JEV Visual", - "owner": "hr98w", - "category": "open-models", - "repoUrl": "https://github.com/hr98w/jev-visual", - "evidenceUrl": "https://github.com/hr98w/jev-visual/blob/19af545f096e8db4c4dd5d47aed42d92ec252111/jev_visual/scoring.py", + "id": "aowang-jev-trade", + "name": "JEV Trade", + "owner": "aowang-ai", + "category": "domain-tools", + "repoUrl": "https://github.com/aowang-ai/jev-trade", + "evidenceUrl": "https://github.com/aowang-ai/jev-trade/blob/df2c9656324a8a75996eb0612de7adcfe3ce6f89/src/model.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/hr98w/jev-visual/blob/19af545f096e8db4c4dd5d47aed42d92ec252111/jev_visual/scoring.py" + "url": "https://github.com/aowang-ai/jev-trade/blob/df2c9656324a8a75996eb0612de7adcfe3ce6f89/src/model.ts" }, - "language": "Python", - "license": "MIT", - "starsAtCapture": 192, + "language": "TypeScript", + "license": "NOASSERTION", + "starsAtCapture": 68, "summary": { - "en": "An educational JEV-like visual inference experiment on Apple Silicon with shared context scoring.", - "zh": "在 Apple Silicon 上的教学向类 JEV 视觉推理实验，共享上下文直接给候选打分。", - "ja": "Apple Silicon 上の教育向け JEV 風ビジョン推論。共有コンテキストで候補を直接採点。" + "en": "A live Hyperliquid trading agent with JEV as a bounded decision layer.", + "zh": "以 JEV 作为有限决策层的 Hyperliquid 实盘交易 Agent。", + "ja": "JEV を限定判断レイヤーに使う Hyperliquid ライブ取引 Agent。" }, "decision": { - "en": "Scores visual or textual candidates in one forward pass and returns calibrated probabilities.", - "zh": "一次前向为视觉或文本候选打分，并返回校准概率。", - "ja": "1 回の前向き計算で視覚／テキスト候補を採点し、校正確率を返します。" + "en": "Chooses among configured trading actions from market and position state.", + "zh": "根据市场与持仓状态，从配置的交易动作中选择。", + "ja": "市場とポジション状態から設定済み取引操作を選びます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "third-hand", - "name": "Third Hand", - "owner": "shhivv", - "category": "browser-computer-use", - "repoUrl": "https://github.com/shhivv/third-hand", - "evidenceUrl": "https://github.com/shhivv/third-hand/blob/430394b35dbb44ff8b303bf19da29b0828d92bd2/Sources/ThirdHand/JevClient.swift", + "id": "appitstudio-awesome-jev", + "name": "Awesome JEV (AppitStudio)", + "owner": "AppitStudio", + "category": "developer-tools", + "repoUrl": "https://github.com/AppitStudio/awesome-jev", + "evidenceUrl": "https://github.com/AppitStudio/awesome-jev/blob/5d654f24aecf992617bbc45e76f32a36eba62f65/README.md", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/shhivv/third-hand/blob/430394b35dbb44ff8b303bf19da29b0828d92bd2/Sources/ThirdHand/JevClient.swift" + "url": "https://github.com/AppitStudio/awesome-jev/blob/5d654f24aecf992617bbc45e76f32a36eba62f65/README.md" }, - "language": "Swift", - "license": "MIT", - "starsAtCapture": 270, + "language": "Python", + "license": "NOASSERTION", + "starsAtCapture": 66, "summary": { - "en": "A Swift client stack that calls JEV while driving local computer-use style helpers.", - "zh": "Swift 客户端栈：在驱动本地 computer-use 辅助逻辑时调用 JEV。", - "ja": "ローカル Computer Use 補助を動かしつつ JEV を呼ぶ Swift クライアント。" + "en": "A curated JEV resource list with runnable typed-decision examples.", + "zh": "带可运行类型化决策示例的 JEV 精选资源列表。", + "ja": "実行可能な型付き判断例を含む JEV 資料一覧。" }, "decision": { - "en": "Requests typed judgments from JEV before applying local automation actions.", - "zh": "在执行本地自动化动作前向 JEV 请求类型化判断。", - "ja": "ローカル自動化の前に JEV へ型付き判断を求めます。" + "en": "Connects learning resources to concrete Choice, Score, and Noul examples.", + "zh": "把学习资源关联到具体 Choice、Score 与 Noul 示例。", + "ja": "学習資料を具体的な Choice、Score、Noul の例に結び付けます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "compact-adviser", - "name": "Compact Adviser", - "owner": "kunchenguid", - "category": "agent-workflows", - "repoUrl": "https://github.com/kunchenguid/compact-adviser", - "evidenceUrl": "https://github.com/kunchenguid/compact-adviser/blob/d1655faa16a22b68bff60c3d7deb0123e1e52a53/packages/codex-plugin/skills/compact-adviser/SKILL.md", + "id": "realzachi:typesafe-adblock", + "name": "TypeSafe Adblock", + "owner": "realZachi", + "category": "browser-computer-use", + "repoUrl": "https://github.com/realZachi/typesafe-adblock", + "evidenceUrl": "https://github.com/realZachi/typesafe-adblock/blob/7e067d243d87b7fe4d511653c0ddcd77b9beee18/src/typesafe.js", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/kunchenguid/compact-adviser/blob/d1655faa16a22b68bff60c3d7deb0123e1e52a53/packages/codex-plugin/skills/compact-adviser/SKILL.md" + "url": "https://github.com/realZachi/typesafe-adblock/blob/7e067d243d87b7fe4d511653c0ddcd77b9beee18/src/typesafe.js" }, - "language": "TypeScript", + "language": "JavaScript", "license": "MIT", - "starsAtCapture": 157, + "starsAtCapture": 64, "summary": { - "en": "A coding-agent skill/plugin that advises when to compact context to save tokens.", - "zh": "编码 Agent 的 Skill/插件：建议何时压缩上下文以节省 token。", - "ja": "いつコンテキストを圧縮してトークンを節約するかを助言するコーディング Agent Skill。" + "en": "An experimental Chrome extension that asks Jev whether candidate DOM elements are ads, then highlights or removes them.", + "zh": "一个实验性 Chrome 扩展，让 Jev 判断候选 DOM 元素是否是广告，再高亮或移除。", + "ja": "候補となる DOM 要素が広告であるかどうかを JEV に尋ね、それらをハイライト表示または削除する実験的な Chrome 拡張機能。" }, "decision": { - "en": "Judges whether the session looks complete enough to compact safely.", - "zh": "判断当前会话是否已足够完整、可以安全压缩。", - "ja": "セッションが十分完了して安全に圧縮できるかを判断します。" + "en": "Batches element text, labels, and link information into Noul questions and applies a threshold.", + "zh": "对元素文本、标签和链接等信息批量询问 Noul，按阈值应用页面操作。", + "ja": "要素のテキスト、ラベル、リンク情報を Noul の質問にバッチ処理し、しきい値を適用します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "logicrw-awesome-jev-projects", - "name": "Awesome JEV Projects", - "owner": "logicrw", - "category": "developer-tools", - "repoUrl": "https://github.com/logicrw/awesome-jev-projects", - "evidenceUrl": "https://github.com/logicrw/awesome-jev-projects/blob/d1b1b8d6c68c1754425778606d20d2cb14b09895/SKILL.md", + "id": "ying-kai-liao-jev-browser", + "name": "JEV Browser", + "owner": "Ying-Kai-Liao", + "category": "browser-computer-use", + "repoUrl": "https://github.com/Ying-Kai-Liao/jev-browser", + "evidenceUrl": "https://github.com/Ying-Kai-Liao/jev-browser/blob/578cff6e701a131733d03256078bb559a45ad188/src/jev.mjs", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/logicrw/awesome-jev-projects/blob/d1b1b8d6c68c1754425778606d20d2cb14b09895/SKILL.md" + "url": "https://github.com/Ying-Kai-Liao/jev-browser/blob/578cff6e701a131733d03256078bb559a45ad188/src/jev.mjs" }, "language": "JavaScript", "license": "MIT", - "starsAtCapture": 264, + "starsAtCapture": 62, "summary": { - "en": "A source-backed JEV ecosystem radar with plain-language discovery and GitHub sync.", - "zh": "有源码依据的 JEV 生态雷达，含白话发现页与 GitHub 同步。", - "ja": "根拠付き JEV エコシステムレーダー。平易な発見 UI と GitHub 同期付き。" + "en": "A browser automation library, CLI, and MCP server pairing LLM plans with JEV actions.", + "zh": "把 LLM 规划与 JEV 动作结合的浏览器自动化库、CLI 与 MCP Server。", + "ja": "LLM の計画と JEV の操作を組み合わせるブラウザー自動化ライブラリ、CLI、MCP サーバー。" }, "decision": { - "en": "Curates which open-source JEV integrations are worth browsing by decision pattern.", - "zh": "按决策模式整理值得浏览的开源 JEV 集成。", - "ja": "意思決定パターン別に、見る価値のある OSS JEV 統合を整理します。" + "en": "Chooses the next browser action and target from the current page observation.", + "zh": "根据当前页面观察选择下一步浏览器动作与目标。", + "ja": "現在のページ観測から次のブラウザー操作と対象を選びます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "hermes-jev-skills", - "name": "Hermes JEV Skills", - "owner": "kerpopule", - "category": "routing-optimization", - "repoUrl": "https://github.com/kerpopule/hermes-jev-skills", - "evidenceUrl": "https://github.com/kerpopule/hermes-jev-skills/blob/a5d89014fbeca5102c5e7ccd3915afcd856505d8/jevkit/choose.py", + "id": "save-token-jev-clean", + "name": "Save Token JEV Clean", + "owner": "IAmUnbounded", + "category": "agent-workflows", + "repoUrl": "https://github.com/IAmUnbounded/save-token-jev-clean", + "evidenceUrl": "https://github.com/IAmUnbounded/save-token-jev-clean/blob/a7007354a8d3747f06ff82130561edb2822a17df/src/client.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/kerpopule/hermes-jev-skills/blob/a5d89014fbeca5102c5e7ccd3915afcd856505d8/jevkit/choose.py" + "url": "https://github.com/IAmUnbounded/save-token-jev-clean/blob/a7007354a8d3747f06ff82130561edb2822a17df/src/client.ts" }, - "language": "Python", + "language": "TypeScript", "license": "MIT", - "starsAtCapture": 335, + "starsAtCapture": 62, "summary": { - "en": "JEV-powered routing, memory, compaction, skill selection, and computer/browser use for Hermes agents.", - "zh": "为 Hermes Agent 提供 JEV 驱动的路由、记忆、压缩、Skill 选择与电脑/浏览器操作。", - "ja": "Hermes エージェント向けに、JEV 駆動のルーティング・記憶・圧縮・Skill 選択・PC/ブラウザ操作。" + "en": "A context cleaner that asks JEV which history to retain, truncate, or drop.", + "zh": "让 JEV 判断哪些历史应保留、截断或丢弃的上下文清理器。", + "ja": "履歴を保持・短縮・削除するか JEV に判断させる文脈クリーナー。" }, "decision": { - "en": "Chooses models, skills, or next computer actions from bounded JEV questions.", - "zh": "用有限 JEV 问题选择模型、Skill 或下一步电脑动作。", - "ja": "有限の JEV 質問でモデル・Skill・次の PC 操作を選びます。" + "en": "Scores conversation items for retention while preserving kept content verbatim.", + "zh": "为对话条目保留价值评分，并原样保留入选内容。", + "ja": "会話項目の保持価値を評価し、残す内容は原文のまま保ちます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "jev-pruner", - "name": "JEV Pruner", - "owner": "tamaratran", - "category": "agent-workflows", - "repoUrl": "https://github.com/tamaratran/jev-pruner", - "evidenceUrl": "https://github.com/tamaratran/jev-pruner/blob/47d017c34eab7690b95f075ce6f4839247c5dc0a/src/jev.ts", + "id": "nidhi-agent-router", + "name": "Agent Router", + "owner": "nidhi-singh02", + "category": "routing-optimization", + "repoUrl": "https://github.com/nidhi-singh02/agent-router", + "evidenceUrl": "https://github.com/nidhi-singh02/agent-router/blob/ad7571f38ea31ffbf3c28391f9e6d6383a7c08ba/packages/router/src/semantic/typesafe-client.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/tamaratran/jev-pruner/blob/47d017c34eab7690b95f075ce6f4839247c5dc0a/src/jev.ts" + "url": "https://github.com/nidhi-singh02/agent-router/blob/ad7571f38ea31ffbf3c28391f9e6d6383a7c08ba/packages/router/src/semantic/typesafe-client.ts" }, "language": "TypeScript", "license": "MIT", - "starsAtCapture": 130, + "starsAtCapture": 58, "summary": { - "en": "A Claude Code plugin that trims long Bash output with TypeSafe JEV before the model sees it.", - "zh": "Claude Code 插件：在模型看到长 Bash 输出前，用 TypeSafe JEV 裁剪。", - "ja": "長い Bash 出力をモデルに渡す前に TypeSafe JEV で刈り込む Claude Code プラグイン。" + "en": "A CLI that routes tasks to coding agents, models, and reasoning effort with JEV.", + "zh": "用 JEV 把任务路由到编码 Agent、模型与推理强度的 CLI。", + "ja": "JEV でタスクをコーディング Agent、モデル、推論強度へ振り分ける CLI。" }, "decision": { - "en": "Decides which output slices stay useful versus safe to drop under a token budget.", - "zh": "在 token 预算下判断哪些输出片段仍有用、哪些可丢弃。", - "ja": "トークン予算の下で、残すべき出力断片と捨ててよい断片を判断します。" + "en": "Ranks eligible routes and effort levels after local safety and quota checks.", + "zh": "在本地安全与配额检查后，对可用路由和推理强度排序。", + "ja": "ローカルの安全・割当確認後に候補ルートと推論強度を順位付けします。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "openjev-verdict-2", - "name": "OpenJEV Verdict 2.0", - "owner": "Heman10x-NGU", - "category": "open-models", - "repoUrl": "https://github.com/Heman10x-NGU/openJev-verdict-2.0", - "evidenceUrl": "https://github.com/Heman10x-NGU/openJev-verdict-2.0/blob/a458733c5f43fc7f30b6e4381636cbfbf8437633/openjev/__init__.py", - "source": { - "type": "github", - "label": "GitHub source", - "url": "https://github.com/Heman10x-NGU/openJev-verdict-2.0/blob/a458733c5f43fc7f30b6e4381636cbfbf8437633/openjev/__init__.py" - }, - "language": "Python", - "license": "Not declared", - "starsAtCapture": 221, + "id": "jegrep", + "name": "jegrep", + "owner": "can1357", + "category": "search-data", + "repoUrl": "https://github.com/can1357/jegrep", + "evidenceUrl": "https://github.com/can1357/jegrep/blob/a280f14f6da8163bde67e0c49f58b23517a02882/src/jev.rs", + "language": "Rust", + "license": "MIT", + "starsAtCapture": 57, "summary": { - "en": "A calibrated ~151M non-autoregressive local decision engine aiming at JEV-style typed answers.", - "zh": "约 151M 的校准非自回归本地决策引擎，目标对齐类 JEV 类型化答案。", - "ja": "約 151M の校正済み非自己回帰ローカル意思決定エンジン。JEV 風の型付き回答を目指す。" + "en": "Semantic grep for live code trees: describe what you need, get files and original line ranges without building an index.", + "zh": "面向实时代码树的语义 grep：用自然语言描述目标，无需建索引即可返回文件与原始行号范围。", + "ja": "ライブ コード ツリーのセマンティック grep: 必要なものを記述し、インデックスを作成せずにファイルと元の行範囲を取得します。" }, "decision": { - "en": "Produces local Noul/Choice/Score-style probabilities without calling hosted JEV.", - "zh": "不调用托管 JEV，在本地产出 Noul/Choice/Score 风格概率。", - "ja": "ホスト型 JEV を呼ばず、ローカルで Noul/Choice/Score 風の確率を出します。" + "en": "JEV scores folders, files, and bounded code passages; local search strategies manage budgets, thresholds, and fallbacks.", + "zh": "JEV 为目录、文件和有限代码片段评分，本地搜索策略负责预算、阈值与回退。", + "ja": "JEV は、フォルダー、ファイル、および制限されたコードパッセージをスコアリングします。ローカル検索戦略は、予算、しきい値、およびフォールバックを管理します。" + }, + "source": { + "type": "github", + "label": "GitHub source", + "url": "https://github.com/can1357/jegrep/blob/a280f14f6da8163bde67e0c49f58b23517a02882/src/jev.rs" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "building-with-jev-skill", - "name": "Building with JEV Skill", - "owner": "dbreunig", - "category": "developer-tools", - "repoUrl": "https://github.com/dbreunig/building-with-jev-skill", - "evidenceUrl": "https://github.com/dbreunig/building-with-jev-skill/blob/04fe3666c6b8b8abfec1271c0e581c823a181f6d/skills/jev/SKILL.md", + "id": "neo4jev", + "name": "Neo4JEV", + "owner": "jexp", + "category": "search-data", + "repoUrl": "https://github.com/jexp/neo4jev", + "evidenceUrl": "https://github.com/jexp/neo4jev/blob/d157bbe496eb91813475156942bef1c6badfb342/src/neo4jev/navigator.py", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/dbreunig/building-with-jev-skill/blob/04fe3666c6b8b8abfec1271c0e581c823a181f6d/skills/jev/SKILL.md" + "url": "https://github.com/jexp/neo4jev/blob/d157bbe496eb91813475156942bef1c6badfb342/src/neo4jev/navigator.py" }, - "language": "Not declared", - "license": "Not declared", - "starsAtCapture": 128, + "language": "Jupyter Notebook", + "license": "MIT", + "starsAtCapture": 57, "summary": { - "en": "An agent skill for writing and improving programs that call JEV / System One.", - "zh": "帮助编写与改进调用 JEV / System One 程序的 Agent Skill。", - "ja": "JEV / System One を呼ぶプログラムの作成・改善を助ける Agent Skill。" + "en": "A Neo4j graph navigator that uses JEV to classify the next relationship.", + "zh": "使用 JEV 判断下一条关系的 Neo4j 图导航器。", + "ja": "JEV で次のリレーションを分類する Neo4j グラフナビゲーター。" }, "decision": { - "en": "Advises how to frame state and questions so JEV returns usable typed answers.", - "zh": "指导如何组织 state 与 questions，让 JEV 返回可用的类型化答案。", - "ja": "使える型付き回答になるよう、state と questions の組み立て方を助言します。" + "en": "Chooses the next graph relationship from the current node and query goal.", + "zh": "根据当前节点与查询目标选择下一条图关系。", + "ja": "現在ノードと検索目標から次のグラフ関係を選びます。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "decider", - "name": "Decider", - "owner": "Mapika", - "category": "open-models", - "repoUrl": "https://github.com/Mapika/decider", - "evidenceUrl": "https://github.com/Mapika/decider/blob/c4daaac28af9fea95d627015cffa2dd5a5926ee6/decider/__init__.py", + "id": "prism-liquidity-agent", + "name": "Prism Liquidity Agent", + "owner": "irfndi", + "category": "domain-tools", + "repoUrl": "https://github.com/irfndi/prism-liquidity-agent", + "evidenceUrl": "https://github.com/irfndi/prism-liquidity-agent/blob/22c67bdbe30bab608226832256a5013ad826b707/engine/jev-service.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/Mapika/decider/blob/c4daaac28af9fea95d627015cffa2dd5a5926ee6/decider/__init__.py" + "url": "https://github.com/irfndi/prism-liquidity-agent/blob/22c67bdbe30bab608226832256a5013ad826b707/engine/jev-service.ts" }, - "language": "Python", - "license": "Apache-2.0", - "starsAtCapture": 180, + "language": "TypeScript", + "license": "MIT", + "starsAtCapture": 54, "summary": { - "en": "One-pass typed decisions with calibrated probabilities, fine-tuned from Qwen3.5-2B.", - "zh": "一次前向的类型化决策与校准概率，基于 Qwen3.5-2B 微调。", - "ja": "Qwen3.5-2B 微調整による、1 パスの型付き意思決定と校正確率。" + "en": "An autonomous liquidity agent that uses JEV inside its rebalancing decision service.", + "zh": "在再平衡决策服务中使用 JEV 的自动化流动性 Agent。", + "ja": "リバランス判断サービスで JEV を使う自律流動性 Agent。" }, "decision": { - "en": "Returns local System One–style answers for Choice, Score, and yes/no style prompts.", - "zh": "对 Choice、Score 与是否类问题返回本地 System One 风格答案。", - "ja": "Choice / Score / 是否プロンプトにローカルな System One 風回答を返します。" + "en": "Evaluates bounded liquidity actions from pool, risk, and position state.", + "zh": "根据池子、风险与持仓状态评估有限流动性动作。", + "ja": "プール、リスク、ポジション状態から限定された流動性操作を評価します。" }, "verification": "source-reviewed", "runtimeVerified": false }, { - "id": "djev-spark", - "name": "djev-spark", - "owner": "mmastrac", - "category": "open-models", - "repoUrl": "https://github.com/mmastrac/djev-spark", - "evidenceUrl": "https://github.com/mmastrac/djev-spark/blob/1444f3e927f83ba508e5b28a4fd4fdd9ecd0976b/README.md", + "id": "oxlint-plugin-jev", + "name": "Oxlint Plugin JEV", + "owner": "wobsoriano", + "category": "safety-review", + "repoUrl": "https://github.com/wobsoriano/oxlint-plugin-jev", + "evidenceUrl": "https://github.com/wobsoriano/oxlint-plugin-jev/blob/18c5bc9097d88344382a98a78a67698c9c7ecf01/src/jev.ts", "source": { "type": "github", "label": "GitHub source", - "url": "https://github.com/mmastrac/djev-spark/blob/1444f3e927f83ba508e5b28a4fd4fdd9ecd0976b/README.md" + "url": "https://github.com/wobsoriano/oxlint-plugin-jev/blob/18c5bc9097d88344382a98a78a67698c9c7ecf01/src/jev.ts" }, - "language": "HTML", - "license": "Not declared", - "starsAtCapture": 152, + "language": "TypeScript", + "license": "MIT", + "starsAtCapture": 52, "summary": { - "en": "A DGX Spark container recipe for running DiffusionGemma NVFP4 structured decisions.", - "zh": "在 DGX Spark 上跑 DiffusionGemma NVFP4 结构化决策的容器配方。", - "ja": "DGX Spark 上で DiffusionGemma NVFP4 構造化意思決定を動かすコンテナレシピ。" + "en": "An Oxlint plugin that evaluates semantic lint rules with JEV.", + "zh": "用 JEV 评估语义 Lint 规则的 Oxlint 插件。", + "ja": "JEV で意味的な lint ルールを評価する Oxlint プラグイン。" }, "decision": { - "en": "Packages local diffusion decision serving so apps can query typed outcomes on-box.", - "zh": "把本地 diffusion 决策服务打包，供应用在机器上查询类型化结果。", - "ja": "ローカル diffusion 意思決定サービスを梱包し、箱内で型付き結果を問い合わせ可能にします。" + "en": "Returns yes-probabilities for configured semantic findings before reporting them.", + "zh": "对配置的语义问题返回 yes 概率，再决定是否报告。", + "ja": "設定した意味的検出に yes 確率を返し、報告可否を決めます。" }, "verification": "source-reviewed", "runtimeVerified": false diff --git a/package.json b/package.json index 84ea70e..b3adb0b 100644 --- a/package.json +++ b/package.json @@ -6,6 +6,7 @@ "scripts": { "catalog:refresh": "node scripts/refresh-curated-projects.mjs", "catalog:export": "node scripts/export-website-data.mjs", + "catalog:readmes": "node scripts/sync-readmes.mjs", "test": "node --test scripts/validate.test.mjs" } } diff --git a/scripts/curate-star50-expansion-2026-09-21.mjs b/scripts/curate-star50-expansion-2026-09-21.mjs new file mode 100644 index 0000000..0837cd0 --- /dev/null +++ b/scripts/curate-star50-expansion-2026-09-21.mjs @@ -0,0 +1,57 @@ +import { readFile, writeFile } from 'node:fs/promises'; + +const catalogueFile = new URL('../data/projects.json', import.meta.url); +const catalogue = JSON.parse(await readFile(catalogueFile, 'utf8')); + +const p = ({ id, name, owner, category, repo, sha, path = 'README.md', stars, language, license, summary, decision }) => ({ + id, name, owner, category, + repoUrl: `https://github.com/${repo}`, + evidenceUrl: `https://github.com/${repo}/blob/${sha}/${path}`, + source: { type: 'github', label: 'GitHub source', url: `https://github.com/${repo}/blob/${sha}/${path}` }, + language, license, starsAtCapture: stars, + summary: { en: summary[0], zh: summary[1], ja: summary[2] }, + decision: { en: decision[0], zh: decision[1], ja: decision[2] }, + verification: 'source-reviewed', runtimeVerified: false, +}); + +const additions = [ + p({ id:'yibie-awesome-jev', name:'Awesome JEV (yibie)', owner:'yibie', category:'developer-tools', repo:'yibie/awesome-jev', sha:'a42aea88b30aeb62b3f165395f15336853e01863', stars:805, language:'Python', license:'Unknown', summary:['A large community directory of public JEV projects, integrations, and discussions.','收录公开 JEV 项目、集成与讨论的大型社区目录。','公開 JEV プロジェクト、連携、議論をまとめた大規模コミュニティ目录。'], decision:['Organizes the ecosystem into browsable implementation and discussion groups.','把生态项目按实现与讨论类型整理为可浏览目录。','実装と議論を参照しやすい分類に整理します。'] }), + p({ id:'v-modal-awesome-jev-tools', name:'Awesome JEV Tools', owner:'v-modal', category:'developer-tools', repo:'v-modal/awesome-jev-tools', sha:'f117e0c368d6e293bf5fdf99244a1173a6dc2ae0', stars:599, language:'', license:'Unknown', summary:['A curated directory focused on tools built for JEV and TypeSafe System One.','聚焦 JEV 与 TypeSafe System One 工具的精选目录。','JEV と TypeSafe System One 向けツールのキュレーション目录。'], decision:['Surfaces practical tools by integration shape and use case.','按集成方式与使用场景筛选实用工具。','連携方式と用途別に実用ツールを紹介します。'] }), + p({ id:'classifier-dev', name:'Classifier.dev', owner:'mrmps', category:'sdk-integrations', repo:'mrmps/classifier-dev', sha:'33ca63816f2bc7e93c3f2d0715f7896500370739', path:'src/jev.ts', stars:396, language:'TypeScript', license:'MIT', summary:['A zero-shot classification service with JEV as its primary typed-decision backend.','以 JEV 为主要类型化决策后端的零样本分类服务。','JEV を主要な型付き判断バックエンドに使うゼロショット分類サービス。'], decision:['Classifies labels and dimensions, with explicit fallback and observability around JEV calls.','用 JEV 判断标签与维度，并提供明确的回退与可观测性。','JEV でラベルと次元を分類し、明示的なフォールバックと観測性を備えます。'] }), + p({ id:'minecraft-agent-jev', name:'Astra + JEV Minecraft Agent', owner:'rmalde', category:'domain-tools', repo:'rmalde/minecraft-agent', sha:'78b40ed59514e5e2abde33a05ce398ecb2c39e05', path:'models.mjs', stars:395, language:'JavaScript', license:'Unknown', summary:['A Minecraft agent where a planner sets objectives and JEV selects legal game actions.','由规划模型设定目标、JEV 选择合法游戏动作的 Minecraft Agent。','プランナーが目標を定め、JEV が合法なゲーム操作を選ぶ Minecraft Agent。'], decision:['Chooses one available action from observed game state and planner objectives.','根据游戏状态与规划目标，从可用动作中选择一个。','ゲーム状態と計画目標から利用可能な操作を 1 つ選びます。'] }), + p({ id:'von-open-system-one', name:'Von', owner:'wfzyx', category:'open-models', repo:'wfzyx/von', sha:'14d09878e89b103bfbbe641f9bed02e4d72c8830', stars:297, language:'Python', license:'Apache-2.0', summary:['An open, local System One decision model with a JEV-compatible interface.','提供 JEV 兼容接口的本地开放 System One 决策模型。','JEV 互換インターフェースを持つローカルのオープン System One 判断モデル。'], decision:['Scores bounded typed choices locally without autoregressive text generation.','在本地为有限类型化选项评分，不做自回归文本生成。','自己回帰テキスト生成を行わず、限定された型付き候補をローカルで評価します。'] }), + p({ id:'anotiawang-awesome-jev', name:'Awesome JEV (AnotiaWang)', owner:'AnotiaWang', category:'developer-tools', repo:'AnotiaWang/awesome-jev', sha:'04e65b59a936b2fed0d40eaec71a0a11e33bb422', stars:181, language:'', license:'CC0-1.0', summary:['A curated list of JEV applications, libraries, and System One resources.','JEV 应用、类库与 System One 资源精选清单。','JEV アプリ、ライブラリ、System One 資料のキュレーション一覧。'], decision:['Groups ecosystem resources so builders can compare implementation patterns.','整理生态资源，方便开发者比较不同实现模式。','エコシステム資料を整理し、実装パターンを比較しやすくします。'] }), + p({ id:'omnijev-awesome-gallery', name:'Awesome JEV Gallery', owner:'OmniJev', category:'developer-tools', repo:'OmniJev/awesome-jev-gallery', sha:'2b84d22ab0fb9e54098788955187feb023c40ab3', stars:131, language:'JavaScript', license:'NOASSERTION', summary:['A gallery of System One papers, open reproductions, and independent evaluations.','汇总 System One 论文、开放复现与独立评测的 Gallery。','System One の論文、オープン再現、独立評価を集めたギャラリー。'], decision:['Connects model implementations with research and evaluation evidence.','把模型实现与研究、评测证据关联起来。','モデル実装を研究および評価の根拠と結び付けます。'] }), + p({ id:'billionsbobby-jevrouter', name:'JevRouter', owner:'BillionsBobby', category:'routing-optimization', repo:'BillionsBobby/JevRouter', sha:'715970774ae8070e958e83ac9b1a780b32a9184c', path:'src/provider.ts', stars:125, language:'TypeScript', license:'MIT', summary:['A lightweight JEV router for models, tools, and subagents.','用于模型、工具与子 Agent 的轻量 JEV 路由器。','モデル、ツール、サブ Agent 向けの軽量 JEV ルーター。'], decision:['Chooses a model, tool, or subagent from caller-supplied candidates.','从调用方提供的候选中选择模型、工具或子 Agent。','呼び出し側が与えた候補からモデル、ツール、サブ Agent を選びます。'] }), + p({ id:'valentynkit-awesome-jev-typesafe', name:'Awesome JEV TypeSafe', owner:'valentynkit', category:'developer-tools', repo:'valentynkit/awesome-jev-typesafe', sha:'7eec7360d502826b51d1c8862c9fd2d76eecf6e4', path:'readme.md', stars:115, language:'JavaScript', license:'CC0-1.0', summary:['A TypeSafe JEV resource list centered on typed, confidence-aware decisions.','围绕类型化、置信度感知决策整理的 TypeSafe JEV 资源列表。','型付きで信頼度を扱う判断を中心にした TypeSafe JEV 資料一覧。'], decision:['Maps resources to Choice, Score, Noul, and integration patterns.','把资源映射到 Choice、Score、Noul 与集成模式。','資料を Choice、Score、Noul、連携パターンに対応付けます。'] }), + p({ id:'hellogumbo-awesome-jev', name:'Awesome Jev', owner:'hellogumbo', category:'developer-tools', repo:'hellogumbo/awesome-jev', sha:'e18fa74fa53e27395a074cf94c7a127e912fb090', path:'data/projects.json', stars:109, language:'JavaScript', license:'CC0-1.0', summary:['The source catalogue behind awesomejev.com, covering repos, integrations, demos, and research.','awesomejev.com 的源数据目录，覆盖仓库、集成、演示与研究。','awesomejev.com の元カタログで、リポジトリ、連携、デモ、研究を収録。'], decision:['Indexes the wider ecosystem while separating repositories, sites, and articles.','索引更广的生态，并区分仓库、网站与文章。','広いエコシステムを索引化し、リポジトリ、サイト、記事を区別します。'] }), + p({ id:'skillranker', name:'Skillranker', owner:'Dicklesworthstone', category:'agent-workflows', repo:'Dicklesworthstone/skillranker', sha:'16743e9f9dee04850d01015d8f5c863a4ed4d0ff', stars:107, language:'Rust', license:'NOASSERTION', summary:['A Rust CLI that ranks agent skills against live session context with JEV.','用 JEV 根据实时会话上下文排序 Agent Skills 的 Rust CLI。','JEV で現在のセッション文脈に対して Agent Skills を順位付けする Rust CLI。'], decision:['Ranks candidate skills and abstains when confidence is below policy.','对候选 Skill 排序，并在置信度低于策略时放弃选择。','候補 Skill を順位付けし、信頼度が基準未満なら選択を見送ります。'] }), + p({ id:'stanley-code-jev', name:'Stanley Code', owner:'devagrawal09', category:'developer-tools', repo:'devagrawal09/stanley-code', sha:'fd092558ebea389c81d44f9b10e826d9a72afaa3', path:'src/adapters/jev.ts', stars:106, language:'TypeScript', license:'MIT', summary:['Bounded JEV workflows for coding agents with a dedicated adapter.','为编码 Agent 提供带专用适配器的有限 JEV 工作流。','専用アダプターを備えたコーディング Agent 向けの限定 JEV ワークフロー。'], decision:['Turns review and coding checkpoints into typed JEV judgments.','把审查与编码检查点转成类型化 JEV 判断。','レビューとコーディングのチェックポイントを型付き JEV 判断に変換します。'] }), + p({ id:'formanator-jev', name:'Formanator', owner:'timrogers', category:'domain-tools', repo:'timrogers/formanator', sha:'548740edef37a4169eef163e4988e64f43a560ec', path:'src/typesafe.rs', stars:98, language:'Rust', license:'MIT', summary:['A CLI and MCP client for benefit claims with optional JEV receipt classification.','支持可选 JEV 收据分类的福利报销 CLI 与 MCP 客户端。','任意の JEV レシート分類を備えた福利厚生申請 CLI / MCP クライアント。'], decision:['Selects the benefit and receipt category, falling back when confidence is low.','选择福利与收据类别，置信度不足时回退。','福利厚生とレシートのカテゴリを選び、信頼度が低い場合はフォールバックします。'] }), + p({ id:'reflex-open-decision-model', name:'Reflex', owner:'kshetrajna12', category:'open-models', repo:'kshetrajna12/reflex', sha:'e21b3b23afdfeee7021a6604fa38f57e7ff5187f', stars:91, language:'Python', license:'MIT', summary:['A small open decision model that recreates the JEV/System One interface on Qwen.','在 Qwen 上复现 JEV/System One 接口的小型开放决策模型。','Qwen 上で JEV/System One インターフェースを再現する小型オープン判断モデル。'], decision:['Returns calibrated probabilities for state plus typed questions.','对状态与类型化问题返回校准概率。','状態と型付き質問に対して較正済み確率を返します。'] }), + p({ id:'dasheng-jev-reading', name:'Dasheng', owner:'wquguru', category:'domain-tools', repo:'wquguru/dasheng', sha:'1bacff4a075527e6c02da242a72d117e7cb3286b', path:'lib/jev.js', stars:90, language:'JavaScript', license:'Unknown', summary:['A reading-practice app that combines streaming ASR with per-word JEV judgments.','把流式 ASR 与 JEV 逐词判断结合的朗读练习应用。','ストリーミング ASR と単語ごとの JEV 判断を組み合わせた音読練習アプリ。'], decision:['Judges word matches, error classes, and sentence similarity from aligned text.','根据对齐文本判断单词匹配、错误类别与句子相似度。','整列済みテキストから単語一致、誤り分類、文の類似度を判断します。'] }), + p({ id:'supercov-jev-quality', name:'Supercov', owner:'supercorp-ai', category:'safety-review', repo:'supercorp-ai/supercov', sha:'55f5ce93a239829c224b89e6749991310be91ea4', path:'crates/supercov-cli/src/quality.rs', stars:85, language:'Rust', license:'MIT', summary:['A code-quality and coverage tool that uses JEV for bounded quality checks.','使用 JEV 做有限质量检查的代码质量与覆盖率工具。','JEV で限定的な品質チェックを行うコード品質・カバレッジツール。'], decision:['Scores whether generated tests and coverage changes meet configured quality criteria.','判断生成测试与覆盖率变化是否满足配置的质量标准。','生成テストとカバレッジ変更が設定した品質基準を満たすか評価します。'] }), + p({ id:'daseinlabs-open-jev', name:'Open JEV', owner:'daseinlabs', category:'open-models', repo:'daseinlabs/open-jev', sha:'8a4fbdf712e78c5ef45509a16aacb81facdd79be', stars:82, language:'Python', license:'Unknown', summary:['An open JEV-style implementation with custom fine-tuning support.','支持自定义微调的开放 JEV 风格实现。','カスタム微調整に対応するオープンな JEV 形式の実装。'], decision:['Runs bounded decision questions on a locally trainable model.','用可本地训练的模型处理有限决策问题。','ローカル学習可能なモデルで限定的な判断質問を処理します。'] }), + p({ id:'savka777-jev-use', name:'JEV Use', owner:'savka777', category:'browser-computer-use', repo:'savka777/jev-use', sha:'8907f85354addfa3d2b78f6a462087e4c73310b8', stars:79, language:'Swift', license:'MIT', summary:['A macOS computer-use harness that drives Accessibility controls without a vision model.','无需视觉模型、通过无障碍控件操作 macOS 的 Computer Use 工具。','視覚モデルなしで Accessibility 要素を操作する macOS Computer Use ツール。'], decision:['Chooses a visible accessibility element and the next allowed action.','选择可见无障碍元素与下一步允许的动作。','表示中の Accessibility 要素と次の許可済み操作を選びます。'] }), + p({ id:'jev-chat', name:'JEV Chat', owner:'w3cj', category:'interfaces', repo:'w3cj/jev-chat', sha:'e543aba8c21b57a28a748ef41966502130f0f69e', path:'apps/server/src/jev/pools.ts', stars:71, language:'TypeScript', license:'MIT', summary:['A tool-using chat interface where JEV chooses only from code-supplied reply and tool options.','由 JEV 仅从代码提供的回复与工具选项中选择的工具型聊天界面。','JEV がコード提供の返答・ツール候補だけから選ぶツール利用チャット。'], decision:['Selects tools, arguments, and reply fragments from bounded pools.','从有限候选池中选择工具、参数与回复片段。','限定プールからツール、引数、返答断片を選びます。'] }), + p({ id:'grok-bot-jev', name:'Grok Bot JEV', owner:'Bodila51', category:'routing-optimization', repo:'Bodila51/grok-bot-jev', sha:'1583e09928c138aeac0aa89818c67ea41f08e807', stars:68, language:'Python', license:'MIT', summary:['A JEV decision layer for Grok Bot with usage gates and skill templates.','为 Grok Bot 提供用量闸门与 Skill 模板的 JEV 决策层。','使用量ゲートと Skill テンプレートを備えた Grok Bot 向け JEV 判断レイヤー。'], decision:['Routes bounded bot decisions before more expensive generation runs.','在更昂贵的生成前路由有限的 Bot 决策。','高価な生成前に限定された Bot 判断をルーティングします。'] }), + p({ id:'aowang-jev-trade', name:'JEV Trade', owner:'aowang-ai', category:'domain-tools', repo:'aowang-ai/jev-trade', sha:'df2c9656324a8a75996eb0612de7adcfe3ce6f89', path:'src/model.ts', stars:68, language:'TypeScript', license:'NOASSERTION', summary:['A live Hyperliquid trading agent with JEV as a bounded decision layer.','以 JEV 作为有限决策层的 Hyperliquid 实盘交易 Agent。','JEV を限定判断レイヤーに使う Hyperliquid ライブ取引 Agent。'], decision:['Chooses among configured trading actions from market and position state.','根据市场与持仓状态，从配置的交易动作中选择。','市場とポジション状態から設定済み取引操作を選びます。'] }), + p({ id:'appitstudio-awesome-jev', name:'Awesome JEV (AppitStudio)', owner:'AppitStudio', category:'developer-tools', repo:'AppitStudio/awesome-jev', sha:'5d654f24aecf992617bbc45e76f32a36eba62f65', stars:66, language:'Python', license:'NOASSERTION', summary:['A curated JEV resource list with runnable typed-decision examples.','带可运行类型化决策示例的 JEV 精选资源列表。','実行可能な型付き判断例を含む JEV 資料一覧。'], decision:['Connects learning resources to concrete Choice, Score, and Noul examples.','把学习资源关联到具体 Choice、Score 与 Noul 示例。','学習資料を具体的な Choice、Score、Noul の例に結び付けます。'] }), + p({ id:'save-token-jev-clean', name:'Save Token JEV Clean', owner:'IAmUnbounded', category:'agent-workflows', repo:'IAmUnbounded/save-token-jev-clean', sha:'a7007354a8d3747f06ff82130561edb2822a17df', path:'src/client.ts', stars:62, language:'TypeScript', license:'MIT', summary:['A context cleaner that asks JEV which history to retain, truncate, or drop.','让 JEV 判断哪些历史应保留、截断或丢弃的上下文清理器。','履歴を保持・短縮・削除するか JEV に判断させる文脈クリーナー。'], decision:['Scores conversation items for retention while preserving kept content verbatim.','为对话条目保留价值评分，并原样保留入选内容。','会話項目の保持価値を評価し、残す内容は原文のまま保ちます。'] }), + p({ id:'ying-kai-liao-jev-browser', name:'JEV Browser', owner:'Ying-Kai-Liao', category:'browser-computer-use', repo:'Ying-Kai-Liao/jev-browser', sha:'578cff6e701a131733d03256078bb559a45ad188', path:'src/jev.mjs', stars:62, language:'JavaScript', license:'MIT', summary:['A browser automation library, CLI, and MCP server pairing LLM plans with JEV actions.','把 LLM 规划与 JEV 动作结合的浏览器自动化库、CLI 与 MCP Server。','LLM の計画と JEV の操作を組み合わせるブラウザー自動化ライブラリ、CLI、MCP サーバー。'], decision:['Chooses the next browser action and target from the current page observation.','根据当前页面观察选择下一步浏览器动作与目标。','現在のページ観測から次のブラウザー操作と対象を選びます。'] }), + p({ id:'nidhi-agent-router', name:'Agent Router', owner:'nidhi-singh02', category:'routing-optimization', repo:'nidhi-singh02/agent-router', sha:'ad7571f38ea31ffbf3c28391f9e6d6383a7c08ba', path:'packages/router/src/semantic/typesafe-client.ts', stars:58, language:'TypeScript', license:'MIT', summary:['A CLI that routes tasks to coding agents, models, and reasoning effort with JEV.','用 JEV 把任务路由到编码 Agent、模型与推理强度的 CLI。','JEV でタスクをコーディング Agent、モデル、推論強度へ振り分ける CLI。'], decision:['Ranks eligible routes and effort levels after local safety and quota checks.','在本地安全与配额检查后，对可用路由和推理强度排序。','ローカルの安全・割当確認後に候補ルートと推論強度を順位付けします。'] }), + p({ id:'neo4jev', name:'Neo4JEV', owner:'jexp', category:'search-data', repo:'jexp/neo4jev', sha:'d157bbe496eb91813475156942bef1c6badfb342', path:'src/neo4jev/navigator.py', stars:57, language:'Jupyter Notebook', license:'MIT', summary:['A Neo4j graph navigator that uses JEV to classify the next relationship.','使用 JEV 判断下一条关系的 Neo4j 图导航器。','JEV で次のリレーションを分類する Neo4j グラフナビゲーター。'], decision:['Chooses the next graph relationship from the current node and query goal.','根据当前节点与查询目标选择下一条图关系。','現在ノードと検索目標から次のグラフ関係を選びます。'] }), + p({ id:'prism-liquidity-agent', name:'Prism Liquidity Agent', owner:'irfndi', category:'domain-tools', repo:'irfndi/prism-liquidity-agent', sha:'22c67bdbe30bab608226832256a5013ad826b707', path:'engine/jev-service.ts', stars:54, language:'TypeScript', license:'MIT', summary:['An autonomous liquidity agent that uses JEV inside its rebalancing decision service.','在再平衡决策服务中使用 JEV 的自动化流动性 Agent。','リバランス判断サービスで JEV を使う自律流動性 Agent。'], decision:['Evaluates bounded liquidity actions from pool, risk, and position state.','根据池子、风险与持仓状态评估有限流动性动作。','プール、リスク、ポジション状態から限定された流動性操作を評価します。'] }), + p({ id:'oxlint-plugin-jev', name:'Oxlint Plugin JEV', owner:'wobsoriano', category:'safety-review', repo:'wobsoriano/oxlint-plugin-jev', sha:'18c5bc9097d88344382a98a78a67698c9c7ecf01', path:'src/jev.ts', stars:52, language:'TypeScript', license:'MIT', summary:['An Oxlint plugin that evaluates semantic lint rules with JEV.','用 JEV 评估语义 Lint 规则的 Oxlint 插件。','JEV で意味的な lint ルールを評価する Oxlint プラグイン。'], decision:['Returns yes-probabilities for configured semantic findings before reporting them.','对配置的语义问题返回 yes 概率，再决定是否报告。','設定した意味的検出に yes 確率を返し、報告可否を決めます。'] }), +]; + +const STAR_FLOOR = 50; +const urls = new Set(additions.map((item) => item.repoUrl.toLowerCase())); +const kept = catalogue.projects.filter((item) => item.starsAtCapture >= STAR_FLOOR && !urls.has(item.repoUrl.toLowerCase())); +catalogue.projects = [...kept, ...additions].sort((a, b) => b.starsAtCapture - a.starsAtCapture || a.name.localeCompare(b.name)); +catalogue.capturedAt = '2026-09-21'; +catalogue.source.batch = '2026-09-21-star50-two-source-and-code-search'; +catalogue.source.policy = 'Project-level deduplication. Public JEV-related GitHub repositories at or above 50 stars are included only after fixed-commit source review. Discovery includes awesomejev.com, logicrw/awesome-jev-projects, GitHub repository search, and GitHub code search. Runtime behavior is not independently verified.'; + +await writeFile(catalogueFile, `${JSON.stringify(catalogue, null, 2)}\n`); +console.log(`Catalogue now has ${catalogue.projects.length} projects at or above ${STAR_FLOOR} stars.`); diff --git a/scripts/export-website-data.mjs b/scripts/export-website-data.mjs index 70a199a..9786395 100644 --- a/scripts/export-website-data.mjs +++ b/scripts/export-website-data.mjs @@ -1,5 +1,6 @@ import { readFile, writeFile } from 'node:fs/promises'; import { resolve } from 'node:path'; +import { createHash } from 'node:crypto'; const output = process.argv[2]; if (!output) throw new Error('Usage: node scripts/export-website-data.mjs '); @@ -7,6 +8,7 @@ if (!output) throw new Error('Usage: node scripts/export-website-data.mjs b.starsAtCapture - a.starsAtCapture || a.name.localeCompare(b.name)); +const over1k = projects.filter((project) => project.starsAtCapture >= 1_000).length; +const categoryCounts = new Map(); +for (const project of projects) categoryCounts.set(project.category, (categoryCounts.get(project.category) ?? 0) + 1); + +const categories = [ + ['browser-computer-use', ['Browser & computer use', '浏览器与电脑操作', 'ブラウザ・PC 操作']], + ['sdk-integrations', ['SDK integrations', 'SDK 与框架集成', 'SDK・フレームワーク']], + ['routing-optimization', ['Routing & optimization', '路由与优化', 'ルーティング']], + ['open-models', ['Open models', '开放模型', 'オープンモデル']], + ['search-data', ['Search & data', '搜索与数据', '検索・データ']], + ['safety-review', ['Safety & review', '安全与审查', '安全性・レビュー']], + ['agent-workflows', ['Agent workflows', 'Agent 工作流', 'Agent ワークフロー']], + ['interfaces', ['Interfaces & automation', '界面与自动化', 'UI・自動化']], + ['developer-tools', ['Developer tools', '开发者工具', '開発者ツール']], + ['domain-tools', ['Domain tools', '垂直工具', '業務特化ツール']], +]; + +const configs = [ + { + file: 'README.md', index: 0, allHeading: `All ${projects.length} projects`, starWord: 'stars', + strong: 'A source-reviewed gallery of JEV-related projects with 50+ GitHub stars — integrations, tools, open models, experiments, and ecosystem resources.', + policy: 'We list source-reviewed JEV-related repositories at or above 50 stars. See where JEV chooses, scores, routes, or filters—while application code keeps control of execution.', + }, + { + file: 'README.zh-CN.md', index: 1, allHeading: `全部 ${projects.length} 个项目`, starWord: 'Star', + strong: '只整理 50+ Star、经过源码核对的 JEV 相关项目、集成、工具、开放模型、实验与生态资源。', + policy: '收录门槛为 GitHub 50 Star 及以上。看看 JEV 如何完成选择、评分、路由与过滤，同时由应用代码掌控执行。', + }, + { + file: 'README.ja.md', index: 2, allHeading: `全 ${projects.length} プロジェクト`, starWord: 'Star', + strong: 'GitHub 50★以上・ソース確認済みの JEV 関連プロジェクト、連携、ツール、オープンモデル、実験、エコシステム資料をまとめています。', + policy: '掲載基準は 50 stars 以上。JEV が選択・採点・ルーティング・フィルタを担い、実行制御はアプリ側に残る事例です。', + }, +]; + +for (const config of configs) { + const url = new URL(`../${config.file}`, import.meta.url); + let text = await readFile(url, 'utf8'); + text = text.replace(/[^<]+<\/a>/, `${config.allHeading}`); + text = text.replace(/

[^<]+<\/strong><\/p>/, `

${config.strong}

`); + text = text.replace(/

(?:We only list|收录门槛|掲載の中心)[^<]+<\/p>/, `

${config.policy}

`); + text = text.replace(/(\s*\s*)\d+(<\/strong><\/td>\s*)\d+(<\/strong><\/td>\s*)\d+(<\/strong><\/td>\s*)\d{4}-\d{2}-\d{2}/, `$1${projects.length}$2${over1k}$3${categoryCounts.size}$4${catalogue.capturedAt}`); + + const categoryMarkup = `

\n${categories.map(([key, labels], i) => ` ${labels[config.index]} · ${categoryCounts.get(key) ?? 0}${i === categories.length - 1 ? '' : i === 4 ? '
' : ' ·'}`).join('\n')}\n

`; + text = text.replace(/

(?:Browse by category|按分类浏览|カテゴリから探す)<\/h2>\s*

[\s\S]*?<\/p>/, (block) => `${block.match(/^ `- [${project.name}](${project.repoUrl}) · ${project.starsAtCapture.toLocaleString('en-US')} ${config.starWord}`).join('\n'); + const replacement = `\n## ${config.allHeading}\n\n${list}\n\n## BeatAPI`; + text = text.replace(/(?:<\/a>\s*)?## (?:All \d+ projects|全部 \d+ 个项目|全 \d+ プロジェクト)[\s\S]*?\n## BeatAPI/, replacement); + text = text.replace(/\n[\s\S]*$/, ''); + await writeFile(url, text); +} + +console.log(`Synced ${projects.length} projects across ${configs.length} READMEs.`); diff --git a/scripts/validate.test.mjs b/scripts/validate.test.mjs index 2749664..40b0858 100644 --- a/scripts/validate.test.mjs +++ b/scripts/validate.test.mjs @@ -9,7 +9,8 @@ const catalogue = JSON.parse( test('catalogue metadata is explicit', () => { assert.equal(catalogue.schemaVersion, 3); assert.match(catalogue.capturedAt, /^\d{4}-\d{2}-\d{2}$/); - assert.equal(catalogue.projects.length, 125); + assert.equal(catalogue.projects.length, 147); + assert.ok(catalogue.projects.every((project) => project.starsAtCapture >= 50)); }); test('every project keeps repository and fixed-commit evidence links', () => { @@ -60,7 +61,8 @@ test('README identity and project-owned cover stay present', async () => { assert.match(japaneseReadme, /

概要<\/h2>/); for (const localizedReadme of [readme, chineseReadme, japaneseReadme]) { assert.match(localizedReadme, /
\s*/); - assert.match(localizedReadme, /
125<\/strong><\/td>/); + assert.match(localizedReadme, /147<\/strong><\/td>/); + assert.doesNotMatch(localizedReadme, /GitHub 100|100\+ Star|100 stars/); assert.match(localizedReadme, /\/v1\/systemone/); assert.match(localizedReadme, /jev-1\.13/); }