GitHub AI 热门项目 · 2026-07-15

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

autonomous red teaming platform; multi-agent offensive-security meta-harness

The Framework for Building Agents

access to david ondrej's personal agent skills

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

The open-source AI workbench for scientific research

Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.

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.

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

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

Everything I know about running LLMs locally

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

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.

Use ChatGPT Developer Mode as a local coding agent for your repo through MCP.

Open-source @agent mentions for Slack and GitHub. OpenTag routes tagged requests to Codex, Claude Code, then returns results in thread.

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！

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。

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.

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。

Agent-driven media library for your cloud drives (115 / Quark / 光鸭 GuangYaPan).

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.

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

SkillSpec makes agent skills followable, testable, and provable with Doctor risk reports, guided imports, structured contracts, and alignment proof.

Give your AI agent eyes and hands on iOS Simulator and Android emulator/devices.

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.

The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.

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。

Qwen-AgentWorld: Language World Models for General Agents

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

Local-first, zero-trust agentic IDE for verifiable autonomous software development.