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
本周榜单最值得关注的是 xai-org/grok-build，将近两万 star 的势头说明，xAI 将 Grok 编程 Agent 工具链直接开源这一动作精准踩中了开发者痛点——全屏 TUI、鼠标交互、可扩展架构，这是继 Claude Code、Gemini CLI 之后，头部模型阵营第一个正式开源的编程 Agent 前端框架，抢占生态的意图相当明显。紧随其后的 langchain-ai/openwiki 则切入了一个被长期忽视的方向：随着 Codebase 里 Agent 数量爆增，"谁来写文档、谁来维护文档"已成真实痛点，用 CLI 自动生成并持续维护 Agent 文档，思路务实。整体来看本周有一条清晰主线——围绕 Agent 的基础设施正在快速成型，从鉴权网关（open-connector）到技能市场（skills），Agent 的"周边生态"建设已全面铺开。值得警惕的是，专门针对 GPT-5.6 的破甲提示词包也挤进了榜单，这本身就是一个信号：模型能力越强，边界探测的社区热情就越高涨。
| # | 项目 | Star | 语言 | 创建 |
|---|---|---|---|---|
| 1 | xai-org/grok-build SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible. | 18,780 | Rust | 2026-07-14 |
| 2 | langchain-ai/openwiki OpenWiki is a CLI that writes and maintains agent documentation for your codebase. | 12,303 | TypeScript | 2026-06-22 |
| 3 | elder-plinius/T3MP3ST autonomous red teaming platform; multi-agent offensive-security meta-harness | 4,940 | 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. | 2,931 | TypeScript | 2026-06-29 |
| 5 | davidondrej/skills access to david ondrej's personal agent skills | 2,591 | Shell | 2026-06-24 |
| 6 | synthetic-sciences/openscience The open-source AI workbench for scientific research | 2,575 | 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. | 2,310 | 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。 | 2,039 | 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. | 1,731 | 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. | 1,701 | Python | 2026-07-06 |
| 11 | jamesob/local-llm Everything I know about running LLMs locally | 1,559 | 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 | 1,477 | 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. | 1,364 | TypeScript | 2026-06-24 |
| 14 | 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！ | 1,308 | Python | 2026-06-20 |
| 15 | 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。 | 1,083 | Python | 2026-07-10 |
| 16 | fancydirty/mediary-scout Agent-driven media library for your cloud drives (Quark 夸克 / 115 / 光鸭 GuangYa / 123网盘 / 天翼 Tianyi) | 1,078 | TypeScript | 2026-06-21 |
| 17 | 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. | 1,064 | TypeScript | 2026-06-28 |
| 18 | abundantbeing/hermes-browser-extension Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime. | 1,055 | JavaScript | 2026-06-24 |
| 19 | tandpfun/wardrobe Your clothes, extracted and organized with gpt-image. | 1,049 | JavaScript | 2026-07-16 |
| 20 | 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. | 991 | Python | 2026-07-02 |
| 21 | lycorp-jp/sim-use Give your AI agent eyes and hands on iOS Simulator and Android emulator/devices. | 942 | Swift | 2026-06-26 |
| 22 | 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。 | 896 | TypeScript | 2026-07-05 |
| 23 | 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. | 895 | — | 2026-06-28 |
| 24 | HKUDS/OpenOPC OpenOPC: Build Your Personal AI-Native Company — Self-Built, Self-Run, Self-Grown | 883 | Python | 2026-07-01 |
| 25 | uzairansaruzi/hermex Native iPhone app for your Hermes agent | 863 | Swift | 2026-07-02 |
| 26 | modiqo/waggle Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world. | 857 | Rust | 2026-07-08 |
| 27 | 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. | 855 | Python | 2026-07-04 |
| 28 | QwenLM/Qwen-AgentWorld Qwen-AgentWorld: Language World Models for General Agents | 843 | Python | 2026-06-22 |
| 29 | mereyabdenbekuly-ctrl/clodex-ide Local-first, zero-trust agentic IDE for verifiable autonomous software development. | 839 | TypeScript | 2026-07-12 |
| 30 | ai4s-research/open-science Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills. | 823 | TypeScript | 2026-07-03 |
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。