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
Emacs Lisp implementation of the Model Context Protocol
Connect Claude.ai to Twitter/X — without paying $100/month for the official API.
Udemy & Hotmart course downloader, YouTube downloader (yt-dlp GUI, 1,800+ sites) + desktop app for AI agents: Claude Code, Codex, Gemini CLI, Ollama.
A JSON-native lambda calculus runtime with metacircular evaluation, designed as an MCP (Model Context Protocol) server. Enables language models to evolve tools dynamically through metaprogramming.
A simple, locally hosted Web Search MCP server for use with Local LLMs
Model Context Protocol server to use ClickHouse® databases in your AI agents
Model Context Protocol servers you can actually run yourself.
![GitHub Release][releases] ![GitHub Activity][commits]  ![HACS][hacs] ![BuyMeCoffee][buymecoffee]
This project is in its early stages, and the README is currently minimal.
The GPT-RAG MCP service deploys a Python MCP server built with FastMCP and Starlette. It is consumed by GPT-RAG through the orchestrator mcp strategy and is not tied to an AutoGen-specific runtime.
RefactorMCP is a Model Context Protocol server that exposes Roslyn-based refactoring tools for C#.
This is a 12306 ticket search server based on the Model Context Protocol (MCP).
Agent Skills
AetherViz Master - 互动教育可视化建筑师，将任意教学主题转化为沉浸式3D交互网页
HEY CLI and Agent Skills
High-performance AI coding agent CLI written in Rust with zero unsafe code
A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness.
A multi-agent workflow system for GitHub Copilot in VS Code that brings structure, quality gates, and long-term memory to AI-assisted development.
Generate realistic synthetic security logs for cybersecurity threat hunting training and research.
A comprehensive development toolkit designed following Anthropic's Claude Code Best Practices for AI-assisted software development.
Powered by , this project orchestrates 14 , each modeled after world-class experts in their domain. They ideate products, make decisions, write code, deploy, and market - without human intervention.
The Pi extensions and skills I use to keep long agent sessions useful without building a fake operating system around them.
Tell your coding agent to do real, multi-step work, then Smithers runs it for minutes or days: watch every step live, gate the risky ones behind human approvals, and rewind, fork, or replay any run.
[Documentation] [Quick Start] [简体中文] [Tiếng Việt]
An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.