AI-native programmer
- 83+ merged upstream PRs, including Openclaw, PyTorch, vLLM, Deer Flow, Mem0, LightRAG, AstrBot, Qdrant, Numpy, AgentScope, DeepTutor, Qwen Code, QwenPaw, Google ADK, Pydantic AI, Ktransformers, Microsoft Agent Framework, LiveKit Agents, Mooncake, Pymilvus, HiveMind.
- 11 public projects, led by LLM-Wiki, KnowFoundry-RAG-Console, Codex-Pet-Live, OpenSense, vectorpeak-blogs.
| Area | Project | Stars | Notes |
|---|---|---|---|
| Applied agents | KnowFoundry-RAG-Console | 29+ | A console project for knowledge-base and RAG workflows, used to capture engineering practice for retrieval-augmented generation apps |
| Applied agents | Codex-Pet-Live | new+ | A Windows desktop Codex pet runtime for hosting, displaying, and driving interactive desktop companions |
| Applied agents | vectorpeak-blogs | new+ | Personal blog and knowledge site for technical learning, deep learning practice, algorithm notes, and staged reflections |
| Applied agents | Fill-Contributions-Graph | new+ | A utility for backfilling and maintaining GitHub contribution graph activity |
| Applied agents | lingban-ai-chat | new+ | Lingban AI chat Android client and backend API repository |
| Coding agents | OpenSense | new+ | Daily PR opportunity finder for known open-source repositories |
| Coding agents | vectorpeak-agent-skills | new+ | A reusable Agent and Codex skill library for software engineering, knowledge work, and professional workflow automation |
| LLM tooling | LLM-Wiki | 30+ | A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methods, and AI engineering practices |
| Research | carbon-tower-predictor | new+ | An industrial carbonization tower outlet temperature prediction project using historical DCS sensor data for trend forecasting, anomaly warning, and predictive maintenance |
| Research | industrial-fault-text-classifier | new+ | BERT-based industrial equipment fault text classification for repair-ticket analysis, fault recognition, and risk warning |
| Research | kaggle-tabular-forge | new+ | A goal-driven Kaggle tabular experiment factory covering feature mining, OOF discipline, deep stacking, and AI review workflows |
| Project | PR | What I Fixed |
|---|---|---|
| #188961 | Fix Windows target determination for POSIX changed-file paths |
|
| #188830 | Fixed cross-platform CI test target detection by normalizing Git-style and Windows-style test paths |
|
| #47099 | [Bugfix] Align OpenCV video metadata timeline |
|
| #31963 | BUG: avoid invalid Meson identifiers for f2py libraries |
|
| #31934 | BUG: respect pathsep for f2py include paths |
|
| #31906 | BUG: support PathLike paths in DataSource methods |
|
| #2071 | fix(cli): detect bound ports before launch |
|
| #2770 | [Bugfix] Reject empty keys in HTTP metadata server |
|
| #2587 | Preserved empty values in the Mooncake Store REST GET API so clients can reliably read cache metadata and blank fields |
| Project | PR | What I Fixed |
|---|---|---|
| #111333 | Reject blank extract URLs |
|
| #110502 | Reject malformed embedding batch JSONL bytes |
|
| #110495 | Preserve reverse-proxy path prefixes |
|
| #108567 | Add PowerShell instructions to the minimal chat example |
|
| #108548 | Preserve intraword underscores in outbound text |
|
| #105448 | OpenRouter OAuth denial redirects show provider errors |
|
| #105397 | Run ts-topology entrypoint on Windows |
|
| #104935 | Render validation array indices with brackets |
|
| #104853 | Send fragment image URLs as media |
|
| #104498 | Avoid logging raw duplicate card-action tokens |
|
| #104470 | Reject non-finite tool schema numbers |
|
| #102649 | Detect MIME from encoded URL extensions |
|
| #101815 | Split encoded video URLs from captions |
|
| #99180 | Reject tools/call requests with non-object arguments |
|
| #97972 | CDP auth fails with percent-encoded credentials |
|
| #97630 | Normalize Windows inbound paths case-insensitively |
|
| #4278 | Encode artifact URL path segments |
|
| #9213 | Return HTTP errors for failed skill downloads |
|
| #9175 | Validate dashboard account username updates |
|
| #9141 | Enforce ownership when reading ChatUI sessions |
|
| #9085 | Reject non-200 download responses |
|
| #9084 | Enable only synced ModelScope MCP servers |
|
| #8971 | Fixed a path traversal vulnerability in knowledge base upload filenames by validating filename boundaries and blocking directory escape |
|
| #8968 | Fixed a path traversal vulnerability in plugin upload filenames by validating filename boundaries and blocking directory escape |
|
| #608 | Avoid crashes on malformed Markdown hash links |
|
| #602 | Preserve zero LlamaIndex chunk overlap |
|
| #6704 | Reject fractional readTextFile limits |
|
| #6587 | Preserve MCP URL query suffixes |
|
| #6483 | Reject Windows-style workspace artifact paths |
|
| #6455 | Reject fractional LSP limit inputs |
|
| #6413 | Align monitor limit parameter schemas |
|
| #6381 | Require integer ReadFile pagination params |
|
| #6344 | Preserve glued automation history records |
|
| #6323 | Avoid null OpenAPI schema types |
|
| #6317 | Preserve partial remote input JSONL records |
|
| #6243 | Preserve descriptionless tools |
|
| #6033 | Parse tagged thinking for GLM responses |
|
| #6029 | Support Windows-style tilde paths |
|
| #5914 | Harden remaining source path validation |
|
| #5911 | Normalize source slug validation errors |
|
| #5829 | Reject unsafe source slugs before deletion |
|
| #5783 | Reject userinfo URLs in WebFetch validation |
|
| #5841 | Recover whitespace-prefixed tool-call JSON arguments |
|
| #5766 | Recover JSON objects after leading whitespace |
|
| #5750 | Route plugin market details through link guard |
|
| #6328 | Preserve image format for Bedrock images |
|
| #6306 | Preserve provider status errors |
|
| #6305 | Avoid mutating raw tool schemas for Responses |
| Project | PR | What I Fixed |
|---|---|---|
| #5963 | Encode dynamic URL path segments |
|
| #2004 | Reject mutating find commands as read-only |
|
| #1954 | Reject negative grep pagination values |
|
| #6314 | Avoid mutating event validation input |
|
| #6288 | Decode shell skill output as UTF-8 |
|
| #6327 | Preserve HTTPX event hooks |
|
| #6282 | Give a clear error for non-positive concurrency max_running |
|
| #6267 | Reject non-positive OnlineEvaluator.max_concurrency |
|
| #6251 | Write relative schema refs for AgentSpec files |
|
| #6228 | Reject non-positive max_concurrency |
|
| #6143 | Fix absolute schema_path handling in Dataset.to_file |
|
| #6142 | Avoid duplicating /v1 in base_url |
|
| #6140 | Clarify end_strategy values in agent spec |
|
| #6916 | Python: raise ValueError for malformed data URIs |
|
| #6905 | Python: accept AG-UI state data URI parameters |
|
| #6903 | Python: normalize single Anthropic tools |
|
| #6818 | Python: accept A2A data URI media parameters |
|
| #28 | Improved event connection handling and reconnection logic, strengthening disconnect recovery and long-running connection stability |
| Project | PR | What I Fixed |
|---|---|---|
| #3362 | Recover vectors when payload id is missing |
|
| #3354 | Handle DocStatus bulk item failures |
|
| #3324 | Prevent task ID URL path injection |
|
| #3316 | Fixed a path traversal vulnerability in resource file generation by validating directory boundaries and preventing unauthorized writes or overwrites |
|
| #9723 | Parse Windows snapshot mappings |
|
| #9677 | Preserve empty result shape for zero-limit batches |
|
| #3673 | Allow null auto_id primary column in DataFrame insert |
|
| #3658 | Preserve remote upload prefixes on Windows |
AI-native programmer
- 83+ merged upstream PRs，包括 Openclaw, PyTorch, vLLM, Deer Flow, Mem0, LightRAG, AstrBot, Qdrant, Numpy, AgentScope, DeepTutor, Qwen Code, QwenPaw, Google ADK, Pydantic AI, Ktransformers, Microsoft Agent Framework, LiveKit Agents, Mooncake, Pymilvus, HiveMind。
- 11 个公开项目，代表项目包括 LLM-Wiki, KnowFoundry-RAG-Console, Codex-Pet-Live, OpenSense, vectorpeak-blogs。
| Area | Project | Stars | Notes |
|---|---|---|---|
| Applied agents | KnowFoundry-RAG-Console | 29+ | 面向知识库和 RAG 工作流的控制台项目，用于沉淀检索增强生成应用的工程实践 |
| Applied agents | Codex-Pet-Live | new+ | 面向 Windows 桌面的 Codex 宠物运行时，用于承载、展示和驱动交互式桌面宠物 |
| Applied agents | vectorpeak-blogs | new+ | 个人博客与知识站点，用于记录技术学习、深度学习实践、算法题解与阶段性思考 |
| Applied agents | Fill-Contributions-Graph | new+ | GitHub Contribution Graph 荒漠绿化治理工程 |
| Applied agents | lingban-ai-chat | new+ | 灵伴 AI 聊天 Android 客户端与后端 API 仓库 |
| Coding agents | OpenSense | new+ | 面向已知开源项目的每日 PR 机会发现工具 |
| Coding agents | vectorpeak-agent-skills | new+ | 可复用的 Agent / Codex 技能库，覆盖软件工程、知识工作和职业工作流自动化 |
| LLM tooling | LLM-Wiki | 30+ | 大语言模型知识库，覆盖 LLM、Agent、RAG、训练、评测方法和 AI 工程实践 |
| Research | carbon-tower-predictor | new+ | 工业碳化塔取出液温度预测项目，用历史 DCS 传感器数据进行趋势预测、异常预警与预测性维护 |
| Research | industrial-fault-text-classifier | new+ | 基于 BERT 的化工设备故障文本分类方案，用于报修工单分析、故障类别识别和风险预警 |
| Research | kaggle-tabular-forge | new+ | 面向 Kaggle 表格竞赛的实验工厂，覆盖特征挖掘、OOF 纪律、深度 stacking 和 AI 评审工作流 |
| 项目 | PR | 修复内容 |
|---|---|---|
| #188961 | 修复 POSIX 风格变更文件路径下的 Windows 目标判定。 |
|
| #188830 | 通过规范化 Git 风格和 Windows 风格测试路径，修复跨平台 CI 测试目标检测。 |
|
| #47099 | 对齐 OpenCV 视频元数据时间线。 |
|
| #31963 | 避免 f2py 库生成无效的 Meson 标识符。 |
|
| #31934 | 为 f2py include 路径正确遵循 pathsep。 |
|
| #31906 | 支持 DataSource 方法中的 PathLike 路径。 |
|
| #2071 | 启动前检测已绑定端口。 |
|
| #2770 | 在 HTTP metadata server 中拒绝空 key。 |
|
| #2587 | 保留 Mooncake Store REST GET API 中的空值，使客户端能够可靠读取缓存元数据和空字段。 |
| 项目 | PR | 修复内容 |
|---|---|---|
| #111333 | Reject blank extract URLs |
|
| #110502 | 拒绝格式错误的 embedding batch JSONL 字节。 |
|
| #110495 | 保留反向代理路径前缀。 |
|
| #108567 | 为 minimal chat 示例添加 PowerShell 使用说明。 |
|
| #108548 | 保留出站文本中单词内部的下划线。 |
|
| #105448 | 在 OpenRouter OAuth 拒绝重定向中显示 provider 错误。 |
|
| #105397 | 在 Windows 上运行 ts-topology 入口点。 |
|
| #104935 | 将校验数组索引用方括号渲染。 |
|
| #104853 | 将 fragment 图片 URL 作为 media 发送。 |
|
| #104498 | 避免记录原始重复 card-action tokens。 |
|
| #104470 | 拒绝非有限数值的 tool schema numbers。 |
|
| #102649 | 根据编码后的 URL 扩展名检测 MIME。 |
|
| #101815 | 将编码后的视频 URL 与 captions 分离。 |
|
| #99180 | 拒绝参数不是对象的 tools/call 请求。 |
|
| #97972 | CDP 认证会因百分号编码的凭据而失败。 |
|
| #97630 | 以不区分大小写的方式规范化 Windows 入站路径。 |
|
| #4278 | Encode artifact URL path segments |
|
| #9213 | 在 skill 下载失败时返回 HTTP 错误。 |
|
| #9175 | 校验仪表盘账号用户名更新。 |
|
| #9141 | 读取 ChatUI 会话时强制校验所有权。 |
|
| #9085 | 拒绝非 200 的下载响应。 |
|
| #9084 | 仅启用已同步的 ModelScope MCP 服务。 |
|
| #8971 | 通过验证文件名边界并阻止目录逃逸，修复知识库上传文件名中的路径穿越漏洞。 |
|
| #8968 | 通过验证文件名边界并阻止目录逃逸，修复插件上传文件名中的路径穿越漏洞。 |
|
| #608 | 避免格式错误的 Markdown hash links 导致崩溃。 |
|
| #602 | 保留为零的 LlamaIndex chunk overlap。 |
|
| #6704 | 拒绝小数形式的 readTextFile limit。 |
|
| #6587 | 保留 MCP URL query suffixes。 |
|
| #6483 | 拒绝 Windows 风格的 workspace artifact 路径。 |
|
| #6455 | 拒绝小数形式的 LSP limit 输入。 |
|
| #6413 | 对齐 monitor limit 参数 schema。 |
|
| #6381 | 要求 ReadFile 分页参数为整数。 |
|
| #6344 | 保留粘连的 automation 历史记录。 |
|
| #6323 | 避免空的 OpenAPI schema 类型。 |
|
| #6317 | 保留不完整的远程输入 JSONL 记录。 |
|
| #6243 | 保留没有 description 的工具。 |
|
| #6033 | 解析 GLM 响应中的标记化 thinking。 |
|
| #6029 | 支持 Windows 风格的波浪号路径。 |
|
| #5914 | 强化其余 source path 校验。 |
|
| #5911 | 统一 source slug 校验错误。 |
|
| #5829 | 删除前拒绝不安全的 source slug。 |
|
| #5783 | 在 WebFetch 校验中拒绝 userinfo URL。 |
|
| #5841 | 恢复前置空白后的 tool-call JSON 参数。 |
|
| #5766 | 在前导空白后恢复 JSON 对象。 |
|
| #5750 | 让插件市场详情经过 link guard 路由。 |
|
| #6328 | 保留 Bedrock images 的图像格式。 |
|
| #6306 | 保留 provider status errors。 |
|
| #6305 | 避免为 Responses 修改原始 tool schemas。 |
| 项目 | PR | 修复内容 |
|---|---|---|
| #5963 | 对动态 URL 路径片段进行编码。 |
|
| #2004 | 拒绝把会修改文件的 find 命令当作只读命令。 |
|
| #1954 | 拒绝负数 grep 分页值。 |
|
| #6314 | 避免修改事件校验输入。 |
|
| #6288 | 将 shell skill 输出按 UTF-8 解码。 |
|
| #6327 | 保留 HTTPX event hooks。 |
|
| #6282 | 为非正数 concurrency max_running 给出清晰错误。 |
|
| #6267 | 拒绝非正数的 OnlineEvaluator.max_concurrency。 |
|
| #6251 | 为 AgentSpec 文件写入相对 schema refs。 |
|
| #6228 | 拒绝非正数的 max_concurrency。 |
|
| #6143 | 修复 Dataset.to_file 中绝对 schema_path 的处理。 |
|
| #6142 | 避免在 base_url 中重复拼接 /v1。 |
|
| #6140 | 明确 agent spec 中的 end_strategy 取值。 |
|
| #6916 | Python：对格式错误的 data URI 抛出 ValueError。 |
|
| #6905 | Python：接受 AG-UI state data URI 参数。 |
|
| #6903 | Python：规范化单个 Anthropic tools。 |
|
| #6818 | Python：接受 A2A data URI 媒体参数。 |
|
| #28 | 改进事件连接处理和重连逻辑，增强断线恢复和长连接稳定性。 |
| 项目 | PR | 修复内容 |
|---|---|---|
| #3362 | 在 payload id 缺失时恢复向量。 |
|
| #3354 | 处理 DocStatus 批量 item 失败。 |
|
| #3324 | 阻止任务 ID URL 路径注入。 |
|
| #3316 | 通过验证目录边界并防止未授权写入或覆盖，修复资源文件生成中的路径穿越漏洞。 |
|
| #9723 | 解析 Windows snapshot mappings。 |
|
| #9677 | 保留 zero-limit batches 的空结果形状。 |
|
| #3673 | 允许 DataFrame insert 中的 auto_id 主键列为 null。 |
|
| #3658 | 在 Windows 上保留远程上传 prefixes。 |