近 30 天新建、star 最多的 AI 开源项目 Top 30（数据来自 GitHub 官方 API，每日快照）。
今日导读
本周 AI 开源社区有几个值得重点关注的动向。langchain-ai 推出的 openwiki 以超过 1.1 万 star 强势领跑，定位是为代码库自动生成和维护智能体文档的 CLI 工具，切中了当前 Agent 项目文档混乱、难以维护的痛点，对开发者日常工程实践的价值相当实际。Vercel 的 eve 框架入场 Agent 基础设施赛道，凭借品牌效应快速积累近 3500 star，值得观察它能否在 LangChain、LlamaIndex 之外走出差异化路线。另一个亮点是 cloudflare 的 security-audit-skill，把安全审计拆解为可由编码智能体执行的多阶段流程，输出机器可读的结果，是 AI 落地安全工程领域的具体尝试。整体来看，今日榜单折射出一个清晰趋势：社区正在快速围绕 Agent 能力构建垂直工具链——从文档、认证网关到安全审计、科研工作台，Agent 的基础设施层正在全面补齐。
| # | 项目 | Star | 语言 | 创建 |
|---|---|---|---|---|
| 1 | langchain-ai/openwiki OpenWiki is a CLI that writes and maintains agent documentation for your codebase. | 11,009 | TypeScript | 2026-06-22 |
| 2 | elder-plinius/T3MP3ST autonomous red teaming platform; multi-agent offensive-security meta-harness | 4,666 | TypeScript | 2026-07-02 |
| 3 | vercel/eve The Framework for Building Agents | 3,494 | TypeScript | 2026-06-16 |
| 4 | davidondrej/skills access to david ondrej's personal agent skills | 2,487 | Shell | 2026-06-24 |
| 5 | cloudflare/security-audit-skill A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings | 2,485 | JavaScript | 2026-06-18 |
| 6 | synthetic-sciences/openscience The open-source AI workbench for scientific research | 2,391 | TypeScript | 2026-07-03 |
| 7 | oomol-lab/open-connector Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI. | 2,125 | TypeScript | 2026-06-29 |
| 8 | isjiamu/gzh-design-skill 把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML. | 2,111 | HTML | 2026-07-01 |
| 9 | shy3130/tickflow-stock-panel 自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | 基于 TickFlow 数据源 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源 ,非TickFlow官方项目 | 2,082 | TypeScript | 2026-06-18 |
| 10 | HUANGCHIHHUNGLeo/claude-real-video Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT. | 1,599 | Python | 2026-06-30 |
| 11 | shepherd-agents/shepherd A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents | 1,400 | Python | 2026-06-24 |
| 12 | jamesob/local-llm Everything I know about running LLMs locally | 1,394 | Shell | 2026-07-03 |
| 13 | Forsy-AI/agent-apprenticeship The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents. | 1,314 | Python | 2026-06-19 |
| 14 | rebel0789/codexpro Use ChatGPT Developer Mode as a local coding agent for your repo through MCP. | 1,300 | JavaScript | 2026-06-16 |
| 15 | lyra81604/zhengxi-views 可溯源的郑希(易方达基金经理)投研 Agent Skill——基于他全部公开观点原文 + 有原话佐证的投资方法 + 全市场基金真实数据，能溯源问答、按他框架给基金打分，绝不杜撰。⚠️仅研究学习辅助，不构成投资建议‼️website是郑希主页！ | 1,280 | Python | 2026-06-20 |
| 16 | amplifthq/opentag Open-source @agent mentions for Slack and GitHub. OpenTag routes tagged requests to Codex, Claude Code, then returns results in thread. | 1,251 | TypeScript | 2026-06-24 |
| 17 | larlarua/AutoCVE Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation. | 1,243 | Python | 2026-06-15 |
| 18 | sums001/Windows-Copilot-API Reverse engineered Windows Copilot into an OpenAI-compatible API. Access GPT-4 and GPT-5 models through a simple REST interface without API keys or billing. | 1,117 | Python | 2026-06-19 |
| 19 | lingbol088-spec/Codex-5.5-codex-instruct-5.5 Codex CLI 破甲工具（GPT-5.5） — 注入无限制模式系统指令，关闭所有内容过滤器。 | 1,098 | Python | 2026-06-26 |
| 20 | fancydirty/mediary-scout Agent-driven media library for your cloud drives (115 / Quark / 光鸭 GuangYaPan). | 1,044 | TypeScript | 2026-06-21 |
| 21 | jmerelnyc/Talos GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts. | 994 | Python | 2026-07-02 |
| 22 | abundantbeing/hermes-browser-extension Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime. | 964 | JavaScript | 2026-06-24 |
| 23 | modiqo/skillspec SkillSpec makes agent skills followable, testable, and provable with Doctor risk reports, guided imports, structured contracts, and alignment proof. | 948 | Rust | 2026-06-19 |
| 24 | MDX-Tom/gpt-5.6-instruct A Codex CLI jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex CLI 破甲提示词与测试包。 | 883 | Python | 2026-07-11 |
| 25 | Kulaxyz/self-learning-skills A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time. | 849 | — | 2026-06-28 |
| 26 | lycorp-jp/sim-use Give your AI agent eyes and hands on iOS Simulator and Android emulator/devices. | 839 | Swift | 2026-06-26 |
| 27 | QwenLM/Qwen-AgentWorld Qwen-AgentWorld: Language World Models for General Agents | 820 | Python | 2026-06-22 |
| 28 | anthropics/launch-your-agent Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade it, iterate, and schedule it | 797 | HTML | 2026-06-16 |
| 29 | simonlin1212/Vibe-Research Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录。Vibe-Research 把数据和功能配齐，由你自己的 AI 驱动投资研究。 | 797 | TypeScript | 2026-07-05 |
| 30 | yo-WASSUP/Good-Badminton 🏸 AI Badminton Hawk-Eye System | 788 | Python | 2026-06-20 |
历史日报
数据来源 GitHub Search API；「近 30 天新建 + star 排序」反映新项目热度，与 GitHub Trending 口径略有不同。项目描述为原文，导读为本站编辑内容。