雨云服务器注册绑定微信送首月5折优惠券
低价上云，优惠立享
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
本轮最值得关注的信号，是 xAI 直接开源了 Grok 的编码 Agent 终端框架 grok-build，近两万 star 的量级说明开发者对"可本地运行、可交互扩展的 Agent TUI"的需求已到临界点。LangChain 同步推出的 OpenWiki 则切中另一痛点——Agent 代码库的文档自动维护，这类"给 AI 做后勤"的工具正悄悄升格为基础设施。整体来看，本轮上榜项目有一个清晰的结构性特征：模型能力本身已不再是焦点，围绕 Agent 的配套生态——连接器、技能包、文档生成、工作流方法论——正在密集冒头，社区的竞争重心已明显后移到"如何让 Agent 跑得更稳、接入更广"。另一个不应忽视的信号：针对 GPT-5.6 的越狱提示词包公开上榜，AI 安全攻防已不再是论文里的假设场景，攻击工具的开源化节奏正在加快。
| # | 项目 | Star | 语言 | 创建 |
|---|---|---|---|---|
| 1 | xai-org/grok-build SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible. | 17,240 | Rust | 2026-07-14 |
| 2 | langchain-ai/openwiki OpenWiki is a CLI that writes and maintains agent documentation for your codebase. | 12,194 | TypeScript | 2026-06-22 |
| 3 | elder-plinius/T3MP3ST autonomous red teaming platform; multi-agent offensive-security meta-harness | 4,908 | TypeScript | 2026-07-02 |
| 4 | oomol-lab/open-connector Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI. | 2,874 | TypeScript | 2026-06-29 |
| 5 | davidondrej/skills access to david ondrej's personal agent skills | 2,581 | Shell | 2026-06-24 |
| 6 | synthetic-sciences/openscience The open-source AI workbench for scientific research | 2,558 | TypeScript | 2026-07-03 |
| 7 | 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. | 2,292 | HTML | 2026-07-01 |
| 8 | 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。 | 1,932 | Python | 2026-07-11 |
| 9 | 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. | 1,719 | Python | 2026-06-30 |
| 10 | Sahir619/fable-method The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove. | 1,672 | Python | 2026-07-06 |
| 11 | jamesob/local-llm Everything I know about running LLMs locally | 1,549 | Shell | 2026-07-03 |
| 12 | 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 | 1,458 | Python | 2026-06-24 |
| 13 | amplifthq/opentag Open-source @agent mentions for Slack and GitHub. OpenTag routes tagged requests to Codex, Claude Code, then returns results in thread. | 1,363 | TypeScript | 2026-06-24 |
| 14 | ray-r-ren/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. | 1,316 | Python | 2026-06-19 |
| 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！ | 1,306 | Python | 2026-06-20 |
| 16 | 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. | 1,138 | Python | 2026-06-19 |
| 17 | fancydirty/mediary-scout Agent-driven media library for your cloud drives (Quark 夸克 / 115 / 光鸭 GuangYa / 123网盘 / 天翼 Tianyi) | 1,071 | TypeScript | 2026-06-21 |
| 18 | AlephAITech/WorkBuddyGuide A practical, open-source guide to mastering WorkBuddy through real-world workflows.开源的 WorkBuddy 实战蓝皮书：教程、真实工作流、Skills、MCP、自动化与多智能体实践。 | 1,064 | Python | 2026-07-10 |
| 19 | abundantbeing/hermes-browser-extension Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime. | 1,045 | JavaScript | 2026-06-24 |
| 20 | deer-flow/llm-space A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents. | 1,014 | TypeScript | 2026-06-28 |
| 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. | 990 | Python | 2026-07-02 |
| 22 | modiqo/skillspec SkillSpec makes agent skills followable, testable, and provable with Doctor risk reports, guided imports, structured contracts, and alignment proof. | 979 | Rust | 2026-06-19 |
| 23 | lycorp-jp/sim-use Give your AI agent eyes and hands on iOS Simulator and Android emulator/devices. | 938 | Swift | 2026-06-26 |
| 24 | tandpfun/wardrobe Your clothes, extracted and organized with gpt-image. | 933 | JavaScript | 2026-07-16 |
| 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. | 888 | — | 2026-06-28 |
| 26 | 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。 | 886 | TypeScript | 2026-07-05 |
| 27 | HKUDS/OpenOPC OpenOPC: Build Your Personal AI-Native Company — Self-Built, Self-Run, Self-Grown | 881 | Python | 2026-07-01 |
| 28 | SmileLikeYe/agent-chief Attention is your scarcest resource. Chief is the local-first layer that guards it — turning every agent, alert, and feed into one honest call: interrupt, or not. | 867 | Python | 2026-07-04 |
| 29 | uzairansaruzi/hermex Native iPhone app for your Hermes agent | 856 | Swift | 2026-07-02 |
| 30 | QwenLM/Qwen-AgentWorld Qwen-AgentWorld: Language World Models for General Agents | 840 | Python | 2026-06-22 |
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。