Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs.
Lighthouse for MCP — score any MCP server 0–100.
A comprehensive Model Context Protocol (MCP) server for accessing the PubChem chemical database. This server provides access to over 110 million chemical compounds with extensive molecular...
Offline Model Context Protocol (MCP) server that serves Godot Engine API documentation from a local doc/ folder.
mcp-rails is a Ruby on Rails gem that builds on top of the mcp-rb library to seamlessly integrate MCP (Model Context Protocol) servers into your Rails application.
Building Agents with LLM structured generation (BAML), MCP Tools, and 12-Factor Agents principles
An example personal assistant built with Mastra and MCP (Model Context Protocol) that helps with various daily tasks and information management.
ZhuLing — Zero-config AI Agent framework for Java. One YAML to launch Agents on Spring AI + DDD, with MCP tools, full observability and a ReAct core. Ai Agent 快速开发框架
A Model Context Protocol (MCP) service that provides access to Ansible Automation Platform (AAP) APIs through OpenAPI specifications.
Enterprise Governance Layer (Identity, RBAC, Credentials, Auditing, Logging, Tracing) for the Model Context Protocol SDK
Open-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.
A comprehensive collection of courses and tutorials for learning the - an open protocol that standardizes how AI applications connect to external tools and data sources.
Agent Skills
基于 LLM 的股票智能分析 Skill，为 OpenClaw 提供 A股/港股/美股 技术面分析和 AI 决策建议。
A minimal implementation of Recursive Language Models (RLM) using Claude Code as the scaffold. Implemented by Brainqub3.
LightClaw: The Real Lightweight AI Assistant
managed-agents helps teams move AI agents from demos to production with runtime infrastructure for sessions, tools, approvals, sandboxed execution, memory, credential vaults, audit trails, replayable...
Most SEO tools tell you what's wrong with your site. This one writes the pages.
A compact, operational constitution that turns frontier coding agents (Claude Code, Cursor, etc.) from eager-junior behavior into disciplined principal-engineer execution.
Android 逆向分析全家桶 — 从 APK 反编译到 Frida 动态插桩、从 HTTP 接口提取到 JNI/SO 原生层逆向，覆盖静态分析→动态分析→流量解密→签名追踪的完整链路。支持 Claude Code / Codex 双平台，兼容 macOS、Linux、Windows（PowerShell），一套技能打通 Android 安全研究与授权渗透测试的绝大部分需求。
本项目是微信小程序 AI demo，演示**： 用户在小微对话中与小程序 AI 交互，平台返回**， 用户点击卡片后 **进入小程序的开发者业务页（接力页），在小程序内完成选品、下单、支付。
最近一直在看自动化渗透相关，尝试性写了几个框架，但是最后效果都不太满意。相反，之前当玩具写的 Skill 放在 Claude Code 里面，效果却出乎意料地好。
Skill from : How To Use The Hedge Fund Method To Win Every Single Trade.
面向 NSFC、NSSFC、各类省部级自科、社科申请书的 AI 写作技能集。从近 20 本成功申请书（管理口）中提炼写作范式，覆盖从研究设计、技术路线、立项依据到文献综述等核心撰写环节。
A simple template for creating persistent AI companions that remember you