Awesome Jev

A curated list of TypeSafe Jev resources, SDKs, gateways, agents, MCP servers, applications, benchmarks, examples, and independent System One implementations.

Jev returns typed probabilistic decisions for predefined questions. This list favors resources with a working canonical URL, public evidence, meaningful code or documentation, and a specific explanation of Jev's role.

Last verified: 2026-09-21 · Resources: 231 · Categories: 10

Contents

• Official Jev resources
• SDKs and API clients
• Gateways and integrations
• Agent tools and MCP servers
• Browser and computer-use agents
• Applications and developer tools
• Open System One implementations
• Benchmarks and evaluations
• Examples and learning resources
• Community resources

Official Jev resources

• Introducing System One Models and Jev - TypeSafe's launch announcement for System One Models and Jev.
• TypeSafe AI - Official home for TypeSafe AI, System One Models, and Jev.
• TypeSafe System One API Reference - Official HTTP API reference for System One requests and responses.

SDKs and API clients

• Advocaat - A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.
• daf-jev - Composable Python client and decision toolkit for the TypeSafe Jev API.
• Effective Jev - Independent EffectTS-based fork of the TypeSafe JavaScript and TypeScript SDK.
• Jev for OTP - TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer.
• jev go - Independent Go SDK for TypeSafe AI's Jev and System One API.
• jevclient - Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.
• ruby decision model - Ruby client for decision models such as Typesafe Jev.
• RubyLLM TypeSafe - TypeSafe structured-output provider for RubyLLM 2.
• swift typesafe - Unofficial Swift SDK for TypeSafe.
• System One Adapter for Python - Drop-in TypeSafeClient replacement backed by LLM APIs.
• TypeSafe AI Rust - Independent async and blocking Rust SDK for the TypeSafe AI System One API.
• TypeSafe for Elixir - An Elixir client for TypeSafe AI with typed responses and bounded concurrency.
• TypeSafe JavaScript and TypeScript SDK - The official TypeScript/JavaScript library for the TypeSafe API.
• TypeSafe Python SDK - The official Python library for the TypeSafe API.
• typesafe rs - Latency-first Rust SDK for TypeSafe System One.
• TypeSafe Rust SDK - Community Rust client for the TypeSafe AI API with typed System One request and response support.
• typesafe sdk - Ruby client for typesafe.ai.
• TypeSafe SDK for Elixir - An idiomatic, type-safe Elixir port of the official TypeScript AI SDK (ai / ai-sdk) providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current flagship model and is the first System One model.
• TypeSafe SDK for PHP - PHP client for the TypeSafe AI System One API.
• typesafe sdk swift - Unofficial Swift library for the TypeSafe API.
• typesafe-go - Unofficial Go SDK for the TypeSafe AI API with typed System One requests and responses.
• ZIO TypeSafe AI - Scala 3 and ZIO library for TypeSafe AI's Jev and System One API.

Gateways and integrations

• Hono Jev Router - Route HTTP requests by meaning. A semantic router for Hono powered by Jev.
• Jev on Cloudflare Workers AI - Cloudflare Workers AI model documentation for TypeSafe Jev.
• Jev on Netlify AI Gateway - Netlify AI Gateway access for Jev from Netlify Functions.
• Jev on Vercel AI Gateway - Vercel AI Gateway model access for TypeSafe Jev.
• Jevbridge - ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode. - tacticocc/Jevbridge.
• Jevbridge - ACP and MCP adapter that brings TypeSafe Jev typed decisions and computer use to multiple agent hosts.
• kedi-typesafe - Framework-native TypeSafe Jev integrations for Pydantic AI, LangChain, and Kedi.
• LangChain.js TypeSafe integration - This package contains the LangChain.js integration for TypeSafe System One models.
• Laravel TypeSafe Jev - Community Laravel integration for TypeSafe Jev with typed responses, async requests, dependency injection, and testing fakes.
• LlamaIndex Jev - LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge.
• n8n-nodes-typesafe-ai - n8n community node for branching workflows on TypeSafe System One typed decisions.
• neo4jev - Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships.
• OpenInference TypeSafe Instrumentation - OpenInference instrumentation for tracing TypeSafe AI SDK calls in OpenTelemetry-compatible systems.
• Pydantic AI TypeSafeModel - How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
• switchboard - Guardrail and model router for LLM gateways built on Jev with an independent calibration evaluation.
• typesafe ai rails - Community Rails integration for TypeSafe AI's System One API.
• TypeSafe Jev on OpenRouter - OpenRouter model listings and API access for TypeSafe Jev.
• typesafeify - Add a decorator for dspy Signatures that automatically uses TypeSafe where relevant.

Agent tools and MCP servers

• ask-jev-skill - Hermes skill that calls TypeSafe Jev as a typed tiebreaker for agent decisions.
• commit miner - Classify Git commit diffs and messages with Jev. Bug fixes, security fixes/CWEs, and change types.
• fast dev compaction - Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.
• fast-jev-compaction - Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
• grok-bot-jev - Python decision layer that adds Jev-based usage gates and approval-aware routing to Grok Bot.
• Hermes Jev Skills - Agent skills that use Jev for model routing, memory, compaction, skill selection, and computer-use decisions.
• jev - Unofficial CLI and agent skill for TypeSafe Jev judgments with an OpenRouter fallback.
• jev axi - Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell.
• Jev Codex Router - Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.
• Jev Curate - High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul).
• jev judgment - Agent Skill: send closed coding-agent judgments to TypeSafe Jev.
• jev pref - Turn your AGENTS.md preferences into a fast, Jev-powered AI linter.
• Jev Review MCP - Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
• jev scout - Zero-hallucination repository and crate scout powered by TypeSafe AI Jev System One scoring.
• jev seo - 100% free ₹0 agent-first SEO & GEO CLI suite and MCP server in Rust replacing Semrush and OpenSEO via DuckDuckGo and TypeSafe Jev System One.
• jev shell history - Fish-style zsh history autosuggestions ranked by Jev (TypeSafe).
• Jev Skill - Collection of Jev use cases, workflows, and agent skills for bounded decisions.
• Jev Skill Suggester - Codex skill and Python CLI that recommends an installed skill with TypeSafe Jev.
• jev superpowers - Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions.
• jev tree - Recursive Jev choice over a taxonomy. Select from more than 255 options without breaking TypeSafe Jev's choice cap.
• jev use - Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.
• jev-agent-tool - BYOK CLI, Python API, and local MCP server for typed judgments with TypeSafe Jev.
• jev-cli - Dependency-free CLI and stdio MCP server for TypeSafe Jev Noul, Choice, and Score judgments.
• Jev-cu - Codex computer-use skill that delegates text-only action selection to Jev with local safety gates.
• jev-dsh-decision - Agent-harness plugin that exposes Jev evaluations for tool, skill, and task selection.
• jev-gateway - Gateway that uses Jev to route coding-agent tool choices with fail-open passthrough.
• jev-guard - Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.
• jev-mcp by burnigtm - Local stdio MCP server that exposes TypeSafe Jev judgments for coding agents and MCP clients.
• jev-mcp by jkudish - Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.
• jev-mcp-spring - Java and Spring Boot MCP server that exposes TypeSafe Jev judgments to MCP clients.
• jev-predict-skill - Agent skill that predicts another skill's next closed decision with Jev without running that skill.
• jev-pruner - Claude Code and Codex plugin that uses Jev to trim noisy Bash output before it reaches the main model.
• jev-router - Route to the cheapest model in claude code for your task using jev-router.
• jev-rules - Claude Code plugin that uses Jev to select applicable project rules and map documents.
• jev-sift - Portable agent plugin and MCP tool for batch relevance classification with Jev.
• jevon - Rust command-line interface and MCP server for TypeSafe Jev typed decisions.
• JevRouter - Typed agent router that selects models, subagents, skills, MCP tools, CLIs, and plugins.
• jevwire - Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev).
• pi fast jev compaction - Pi extension: verbatim context compaction with TypeSafe Jev decisions.
• pi warden - Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop.
• pi-jev - TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers.
• pi-jev by TheoOliveira - Pi coding-agent extension for semantic tool routing, skill discovery, and typed Jev decisions.
• pi-jev-auto-mode - Pi coding-agent auto mode that uses Jev to judge Bash, write, and edit tool calls with fail-closed behavior.
• save-token-jev-clean - Cross-agent context-compaction plugins that use Jev to retain, bound, or drop tool results.
• Supercov - Supercov tells your coding agent what to fix and what to test with Jev-based code-quality scoring.
• TypeSafe Agent Skills - Agent skills for building with TypeSafe's System One API.
• typesafe-mcp - mcp connector to give your AI agent direct access to typesafe ai's jev model.
• VexJoy Agent - VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
• wakegate - Ask Jev whether a sleeping agent's wakeup is worth a full LLM turn before you resume it. A fail-open wake gate for long-running agents on Workers, Durable Objects and Node.
• winnow - Calibrated context sieve for Claude Code that filters large tool results before they enter the model context.
• yoshi - Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy.

Browser and computer-use agents

• Jev Browser - Browser use using Typesafe's Jev model.
• jev browser - Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
• Jev Browser Pilot - Bounded browser and desktop automation layer where Jev chooses the next action.
• Jev Browser Use - 5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
• jev canvas - Draw on a tldraw canvas with your voice and a pointing finger. Jev (TypeSafe System One) decides action, target and place in ~350 ms per spoken word.
• Jev Desktop for Codex - Bounded Jev decision loop for Codex Computer Use across browser tabs and native macOS apps.
• jev ego - Fast browser agent for ego lite. One TypeSafe request per step; an agent or Jev picks the move.
• jev for chrome - Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.
• Jev macOS Loop - Open-source native macOS computer-use agent combining local vision and Jev action selection.
• Jev Ultrafast - TypeSafe's Jev picks an operation and an element while a small LLM writes text only for TYPE_TEXT.
• Jev Voice Browser - Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
• jev-recruiter - Local recruiting workspace where Jev screens visible LinkedIn profiles against a hiring brief.
• jev-use - macOS voice and typed computer-use harness that selects actions from the Accessibility tree with Jev.
• jev-voice - macOS voice-control app that uses Whisper and one TypeSafe Jev call per command.
• Mobile Jev - Mobile agent for Mobilerun that uses Jev to choose actions on a real Android device.
• TipTour - Open-Source fast local computer use.
• TypeSafe AdBlock - 🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.
• TypeSafe Computer Use - Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
• unclutter - WXT browser extension: Jev-powered page clutter removal with reusable template rules.

Applications and developer tools

• Blink - Codebase search powered by Jev from @typesafe-ai.
• Distill - Distill is a lightweight coding agent harness and TUI built to get more done with FAR FEWER tokens 🔥.
• EmbodiedJev - MuJoCo robot decision workbench with TypeSafe Jev, MiniCPM, and compatible model APIs.
• Foreman - Software factory foreman based on TypeSafe's Jev model.
• HA-Jev - Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automations, and a conversation agent for Assist.
• invalidate - Agent memory invalidation layer that uses Jev to decide when stored facts are no longer valid.
• is-malicious - A codebase scanner that helps you not run malicous code.
• jev belay - Claude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else.
• Jev Chat - Tool-calling chat application that uses Jev without an LLM writing the reply.
• jev commit - pre-commit hook: one Jev call judges whether your commit message matches the diff, plus debug leftovers, scope creep, and a secret belt.
• Jev Drone - Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz.
• Jev Logs - Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.
• jev moderation bot - A Discord moderation bot built with Python and TypeSafe AI Jev System One.
• jev plays pokemon red - Pokemon Red on PyBoy: code owns the route and the arithmetic, Jev picks at branches in about 100 ms, calibration measured instead of assumed.
• Jev Review - A staged code-review workflow and local dashboard built with TypeSafe Jev.
• Jev Reviewer - Browser-based systematic-review extraction tool that uses Jev to locate quoted evidence in research files.
• Jev Search - Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.
• jev skip - YouTube sponsor skipper that reads the captions and decides at watch time: a probability heatmap on the seek bar, no crowd database.
• Jev Social - Jev-powered Instagram, TikTok, and LinkedIn research: typed routing, real browser evidence, streamed post cards, video capture, and cited socai reports.
• Jev Trade - Live Jev trader on Hyperliquid.
• Jev X Sentiment Analysis - Crypto market intelligence terminal that combines X sentiment, market data, and Jev decisions.
• jev-align - Experimental CLI for improving AI Functions with human labels, uncertain examples, and GEPA.
• jev-preview - Keyboard-driven terminal UI for composing TypeSafe Jev requests and viewing probability responses.
• jev-semgrep - Meaning-based grep that uses Jev to filter lines, paragraphs, structured records, and code by description.
• jev-trader - One AI trade decision every Monad block. Jev on Kuru MON-USDC.
• jev.nvim - Neovim: ask the buffer a question, get a quickfix list. Treesitter splits functions, Jev scores each one, probabilities land as virtual text.
• jevcache - Local decision cache for Jev-class models with deterministic replay and redacted state fingerprints.
• JevCal - Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.
• Jevinik - Stock decision terminal that combines live market evidence with Jev probability estimates.
• Jevmail - Local, read-only Gmail triage application that sorts messages into typed Jev categories.
• JevMeter - Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit.
• JevPilot - Three.js driving simulator with a Jev-powered autopilot.
• JevQL - Semantic SQL for Postgres, powered by Jev.
• jgrep - grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.
• jsort - CLI that orders lines by a plain-English dimension using pairwise Jev judgments.
• killmyidea - Describe your startup idea. Jev decides: kill it, fix it or ship it.
• perch - Semantic code linting tool with a CLI, custom rules, and agent integrations.
• pg-jev - Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
• quackd - One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain, Jev for cheaper steps. Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot or any ROS base. Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM. Simulator, .duck safety contracts, MCP, memory between runs, flocks.
• QuantDinger - Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch your own multi-tenant trading SaaS with built-in user management, billing, payments, and settlement.
• skillranker - Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.
• sqlite-jev - Batched natural-language judgments for SQLite, powered by TypeSafe Jev.
• Stanley - Bounded TypeSafe Jev workflows for coding agents.
• Tax Document Classifier - Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.
• TypeSafe Mario - A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
• typesafe snake - Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code.
• x-scanner - Chrome extension that labels posts on X with typed Jev judgments and a live cost counter.

Open System One implementations

• choosekit - Typed choices and probabilities from models running in llama.cpp.
• CUA-S1 Forms - Open computer-use decision model inspired by Jev that scores form actions in one pass.
• Decider - One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.
• Jeff - A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.
• Jev Visual - Educational Jev-like visual inference project for Apple Silicon with a local UI, CLI, and HTTP API.
• Jevlike - Experimental model for selecting among dynamically supplied text options.
• jevmlx - Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.
• Kev - tiny Jev-like model built on top of Qwen2.5-0.5B you can train and run on your MacBook.
• Laya - Laya evaluates typed questions (choice, score, noul) over any state (text, email, ticket or JSON document) in a single forward pass — 33 ms for one question, 7.2 ms/question batched, measured on a T4. No text generation, so nothing to parse and nothing to hallucinate.
• LitJev - Turn any off-the-shelf LLM into a Jev -like decision layer.
• LLM2Jev - Independent local model adapter that returns Jev-style Choice, Score, and Noul decisions.
• LocalJev - Local Jev-compatible API server backed by DiffusionGemma.
• mini-Jev - Preregistered Qwen3-4B experiment that reads option-letter logits for Jev-style typed decisions.
• NanoJev - A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
• Open Alternative to Jev - Open-weight System One-style model layer for typed, calibrated decisions in one forward pass.
• OpenDecision - Open semantic decision engine that returns structured choices from state, questions, and criteria.
• OpenJev - Open, Jev-compatible System One decision server on DiffusionGemma.
• openjev - Local one-pass option scoring server for Gemma on Apple Silicon using MLX.
• OpenJev by zhihz - Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.
• openjev-sglang - Jev-compatible API endpoint based on open models (prefill-only).
• openJev-verdict-2.0 - Open 149.6M-parameter non-autoregressive decision model with calibrated outputs and a WebGPU playground.
• PlayJev - 🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.
• sarvam-jev - Browser-based Jev-style inference engine for typed decisions on an Indic language model.
• SemIf - Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
• Simple Jev - Turn any open model into a classifier/jev endpoint.
• System One - Experimental local classifier that applies a System One-style single-pass decision interface to open models.
• typesafe-local - Local open-model experiment that returns probability distributions for typed questions without an API key.
• Verdict-open-jev - Open ModernBERT decision model with calibrated uncertainty, benchmark audits, and a WebGPU playground.
• Von - Open non-autoregressive System One decision model with calibrated discrete and ordinal inference.

Benchmarks and evaluations

• jev eval - Benchmark TypeSafe Jev against any OpenRouter model on your own labelled classification data: accuracy, calibration, latency, cost.
• Jev Eval Agent - Agent evaluation harness comparing direct model tool selection with Jev-based routing.
• jev phishing bench - Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.
• Jev Reranker - Calibrated Jev reranker with a reproducible comparison against hosted rerankers and LLM judges.
• jev research eval - Reproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice.
• jev search rerank eval - Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.
• jev sec bench - Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go.
• jev spam eval - Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines.
• jev-agent-failure-benchmark - Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).
• jev-alpha-bench - Evaluation of Jev on financial-news and price-candle signals with reproducible event-level results.
• jev-benchmarks - Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
• jev-code-review-benchmark - Reproducible benchmark comparing Jev, Gemini Flash, and Claude Fable on Python code-review rules.
• jev-measured - Reproducible measurements of Jev API cost, latency, raw output, and accuracy across eight use cases.
• jev-rerank-bench - Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.
• TypeSafe AI Benchmark - This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.
• TypeSafe Workflow Evals - Official workflow evaluations for Jev decision tasks.

Examples and learning resources

• Building with Jev - Agent skill for designing, implementing, and diagnosing programs that call Jev.
• Jev Experiments - Collection of latency-focused TypeSafe Jev demos with separate app documentation and tests.
• Jev for Engineers - Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction. Zero dependencies.
• Jev playground - Public BYOK playground demonstrating Jev decisions for agent gates, routing, review, and operator workflows.
• Jev use cases - Runnable Jev use-case harnesses that demonstrate typed decisions for software workflows.
• json-render - Experimental Jev composition for choosing UI specifications from predefined components.
• Pydantic AI + Jev examples - Runnable Pydantic AI examples that use Jev for safety, routing, and game-state decisions.
• TypeSafe AI StarCraft - TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.
• TypeSafe Documentation and Cookbooks - Official quickstarts, primitive guides, patterns, and Jev cookbooks.
• TypeSafe Jev Examples - Worked examples for TypeSafe's Jev System One decision model, runnable today through OpenRouter.
• TypeSafe Playground - Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.

Community resources

• awesome jev - A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.
• awesome jev - A source-backed Jev project directory with a reusable Jev-only GitHub review workflow.
• awesome jev - A curated list of awesome Jev / TypeSafe System One applications, libraries, and resources.
• awesome jev - 🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.
• awesome jev - A community directory of projects built on Jev, TypeSafe AI's System One model.
• awesome jev - A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.
• Awesome Jev by AppitStudio - Curated Jev resources, runnable examples, and agent skills for typed AI decisions.
• Awesome Jev by TypeSafe - Typed decisions with TypeSafe's Jev, the first System One model.
• Awesome Jev by yibie - A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
• Awesome Jev Gallery - Research gallery of papers, open reproductions, and independent evaluations related to System One models and Jev.
• awesome jev projects - Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync.
• awesome jev tools - A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
• Awesome TypeSafe - A curated list of official resources and community projects for TypeSafe, System One models, and Jev.
• Jevify - An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.
• Learn Jev Tutorials - Independent tutorials for Jev concepts, patterns, confidence, and reliability.

Contributing

Contributions are welcome through pull requests. A submission must explain exactly how Jev is used and link to primary evidence.

This list is released under CC0 1.0 Universal.