1416 个 · Agent 智能体
首个开源 Agent Skill 构建器，通过 vibe workflow 定义 Skill，可运行于 Claude Code、Cursor、Codex 等平台；用于构建 Clawdbot 🦞、为 Lovable 提供 API、为 Slack 和 Lark/Feishu 构建 Bot，主张 Skill 是基础设施而非 prompt。The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.
🔥 官方 Firecrawl MCP Server —— 为 Cursor、Claude 以及其他任意 LLM 客户端增添强大的网页抓取与搜索能力。🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
构建端到端可控的 agent harness。面向生产级 AI agent 的开源 SDK，支持 Python 与 TypeScript —— 兼容任意模型、任意云。Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
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.
TalkToFigma：AI Agent（Cursor、Claude Code、Codex）与 Figma 之间的 MCP 集成，使 Agentic AI 能与 Figma 通信，读取设计并以编程方式修改它们。TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
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.
让 Agent 具备浏览器使用能力的 Claude Skill。A Claude Skill to give your agent the ability to use a web browser
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
三语（繁中 / English / 简中）Agentic AI 学习路线图：从 LLM 基础到多 Agent 系统，收录 240+ 精选资源与动手示例。中文 AI agent 學習地圖。A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。
一款提供 iOS 与 macOS 项目开发工具的 Model Context Protocol (MCP) server 与 CLI，供 Agent 使用。A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
教程、指南与 Agent Skill 目录。Tutorials, Guides and Agent Skills Directories
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.
为 Agent 打造的快速精准代码搜索，相比 grep+read 减少约 98% 的 token 用量。Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
通过 CLI、Model Context Protocol (MCP) server 和 AI Agent Skill 编程访问 Gemini Notebook。Programmatic access to Gemini Notebook - via command-line interface (CLI), Model Context Protocol (MCP) server, and AI agent skills.
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
Awesome MCP Servers —— 精选的 Model Context Protocol 服务器列表。Awesome MCP Servers - A curated list of Model Context Protocol servers
Claude Skill：面向 NotebookLM 的多源内容处理器。支持微信公众号文章、网页、YouTube、PDF、Markdown、搜索查询 → Podcast/PPT/思维导图/测验 等。Claude Skill: Multi-source content processor for NotebookLM. Supports WeChat articles, web pages, YouTube, PDF, Markdown, search queries → Podcast/PPT/MindMap/Quiz etc.
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
类似 v0，但在 Cursor / Claude Code / Windsurf 中使用：可搜索 10,000+ React/Tailwind 组件，用 AI 生成新 UI 并发布你自己的组件——直接在编辑器中完成。Magic MCP 现已成为第 21 个 MCP；本包保持旧配置继续可用。配置方式：21st.dev/mcpIt's like v0, but in your Cursor / Claude Code / Windsurf: search 10,000+ React/Tailwind components, generate new UI with AI, and publish your own — right from your editor. Magic MCP is now the 21st MCP; this package keeps old configs working. Setup: 21st.dev/mcp
用于构建 AI agent 的企业级 AI 开发框架。它提供多 provider LLM 的统一管理、具备高精度检索的安全企业知识库、可视化工作流编排与多 agent 协作。兼容主流 Agent Skill 标准，使开发者能够高效构建生产级 [原文未完整]。An enterprise AI development framework for building AI agents. It provides unified management of multi-provider LLMs, secure enterprise knowledge bases with high-precision retrieval, visual workflow orchestration and multi-agent coordination. Compatible with mainstream Agent Skill standards, it enables developers to efficiently build production-gra
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.
自主红队平台；多 Agent 攻击性安全元框架autonomous red teaming platform; multi-agent offensive-security meta-harness
⚡️ 下一代个人 AI 助手，由 LLM、RAG 和 Agent 循环驱动，支持 computer-use、browser-use 和 coding agent，演示地址：https://demo.openagentai.org⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org
OpenSquilla——token 高效的 AI Agent，同等预算，更高智能密度OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
内嵌于你应用中的 AI agent 工作区，具备 Code 与 Write 双模式。AI agent workspace with Code Write and Design modes built into your application.
5ire 是一款跨平台桌面 AI 助手与 MCP 客户端，兼容主流服务提供商，通过 model context protocol server 支持本地知识库与工具调用。5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .
你正在读这段文字，skill 已经预测到了。一个把每条帖子转化为校准实验的工作流——打分、盲预测、复盘、迭代。未来不奖励努力，只奖励先看见模式的人。一个月 100 万粉丝——不是运气，是系统。You're reading this. The skill predicted it. A workflow that turns every post into a calibrated experiment—score, blind-predict, retro, evolve. The future doesn't reward effort, it rewards those who see the pattern first. 1M followers in a month — not luck, system.
面向常驻 Agent 的开源个人云操作系统。Open-Source Personal Cloud OS for Always-On Agents
面向学术研究与软件开发的半自动研究助手，支持 Claude Code、Codex CLI、Kimi Code CLI 与 OpenCode，覆盖构思、编码、实验、写作与发表全流程。Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.