仓库/Skill 库

面向 long horizon agents 的增量引擎 🌟 喜欢的话请点 Star！Incremental engine for long horizon agents 🌟 Star if you like it!

Pocket Flow：一个仅 100 行代码的 LLM 框架。让 Agent 构建 Agent！Pocket Flow: 100-line LLM framework. Let Agents build Agents!

HexStrike AI MCP Agents 是一个高级 MCP 服务器，让 AI agent（Claude、GPT、Copilot 等）能够自主运行 150+ 网络安全工具，用于自动化渗透测试、漏洞发现、漏洞赏金自动化和安全研究，无缝桥接 LLM 与真实世界的攻击性安全能力。HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

基于 Ray 的易用、可扩展、高性能 Agentic RL 框架（PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL）An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

基于 Rust 核心的多语言文档智能：从 106 种格式、140 种文件扩展名中提取文本、元数据、图像、表格与结构化数据，并支持 371 种语言的代码智能。提供十五种语言绑定，配套 CLI、REST API 与 MCP server。Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

Deeplake 是面向 Agent 的 AI 数据运行时，提供无服务器 postgres 与多模态 datalake，支持可扩展的检索与训练Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

PraisonAI 🦞 — 雇佣一支 24/7 AI 团队。停止编写样板代码，开始交付自主且自我改进的 Agent，能够研究、规划、编码并执行任务。5 行代码即可部署，内置 memory、RAG，支持 100+ LLM。PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

故事创作 AI Agent，应用于小说、剧本、互动游戏与 IP 内容。Story Creation AI Agent for novel, scripts, translation, interactive games, and IP content

🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

✨ Agentic HTML 编辑器——本地 AI agent 编写 HTML，你负责发布。🚀 75 个 Skill × 9 种呈现形式（杂志 · 演示文稿 · 海报 · 小红书/推文 · 原型 · 数据报告 · Hyperframes）。🛡️ 沙箱预览 · 📤 一键发布到微信 / X / 知乎 / HTML / PNG。🔑 零 API key——支持 Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider。✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.

FinRobot：基于 LLM 的开源金融分析 AI Agent 平台 🚀 🚀 🚀FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models

灵活而强大的框架，用于管理多个 AI agent 并处理复杂对话。Flexible and powerful framework for managing multiple AI agents and handling complex conversations

用于构建有状态 Agent 的 Memory 库Memory library for building stateful agents

Plano 是面向 agentic 应用的 AI 原生代理与数据平面，内置编排、安全、可观测性和智能 LLM 路由，让你专注于 agent 核心逻辑。Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

数分钟内（而非数月）将 AI Agents 部署到 Google Cloud。提供生产就绪模板，内置 CI/CD、评估和可观测性。Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.

用于构建 agentic apps 的开源框架，支持 JavaScript、Go、Dart 与 Python，由 Google 在生产环境中构建并使用。Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

原子化构建 AI AgentBuilding AI agents, atomically

AI Agent 治理工具包 —— 提供策略执行、零信任身份、运行沙箱与可靠性工程，覆盖 OWASP Agentic Top 10 全部 10 项。AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

AI 原生网络安全的执行系统——意图转化为受治理的执行，证据成为可运营的记忆，每一次操作都让下一次更优。The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

🐢 面向 LLM Agent 的开源评估与测试库🐢 Open-Source Evaluation & Testing library for LLM Agents

下一代 AI Agent 优化平台：Cozeloop 提供从开发、调试、评估到监控的全生命周期管理能力，解决 AI agent 开发中的挑战。Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.

用于构建复杂创新 RAG 流水线的低代码 MCP 框架A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

ZenML 🙏：从 Pipeline 到 Agent 的一站式 AI 平台。https://zenml.ioZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

🏝️ OASIS：基于一百万 Agent 的开放社交交互仿真。🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.

面向常驻 Agent 的开源个人云操作系统。Open-Source Personal Cloud OS for Always-On Agents

【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试资源平台。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、计算机视觉、自然语言处理、自动驾驶、机器学习、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心跨周期知识。

终端中的 Agent，配备本地工具：编写代码、使用终端、浏览网页。在其之上构建你自己的持久化自主 Agent。Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

面向 AI Agent 的开发者控制平面Developer Control Plane for your AI Agents

一个持久化的开发工作空间，能够自我改进并延续于单个会话之外。A persistent workspace for development work that self-improves and continues beyond one session.

CSGHub 是 OpenCSG 团队开发的全新开源 LLM 管理平台，提供开源与本地化/SaaS 解决方案，功能对标 Hugging Face。兼容 Hugging Face Python SDK，全面掌控 LLM、数据集和 agent 的全生命周期。CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️

由 AI 驱动的虚拟高管团队 —— 单一连贯的高管 persona，由 8 个 Claude 专家 agent 支撑（FastAPI + Next.js）。AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist Claude agents (FastAPI + Next.js).

AI Agent 的开源 context layer。PipesHub 将公司知识（Slack、Drive、Jira、GitHub、Microsoft 365 及 40+ 连接器）转化为权限感知的 workspace，Agent 可对其进行搜索、grep、导航和引用。支持 MCP、SDK 与内置 agent，可自托管。The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.

JVM 的便携式 AI Agent 运行时。一个 @Agent 类可通过一套 SPI 在 Spring AI、LangChain4j、Anthropic 或另外 9 个后端上运行。支持 token 流式输出、工具调用、人工审批，并通过 WebSocket、SSE、gRPC 或 WebTransport/HTTP3 提供治理能力。兼容 MCP、A2A 与 AG-UI 协议。Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

作为记忆层的 Agent SkillsAgent Skills as a Memory Layer

面向 AI Agents 的统一虚拟文件系统。The World's First Unified Virtual Filesystem For AI Agents

面向 LLM 实验和 AI Agent 的评估与追踪Evaluation and Tracking for LLM Experiments and AI Agents