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
claude-mem-lite is a (also called long-term memory or cross-session context) system for — Anthropic's CLI coding agent.
MCP Client as Agent Strategy Plugin with Computer Using Agent (UI-TARS-SDK) support. Dify is not MCP Server but MCP Host.
An mcp server for your food ordering needs.
一个基于 mijiaAPI 3.x 的产品化米家 MCP 服务。它不再要求客户端先理解 did、siid/piid/aiid 这些协议细节，而是优先面向“家庭、房间、设备名、场景名”提供更自然的查询和控制能力。
An MCP server that slurps data from Google News and Google Trends RSS endpoints, optionally distills it with LLM/NLP, and barfs out structured results.
MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dispatch, sessions, async jobs, agent dialogues.
Загружает метаданные и код конфигураций 1С в графовую базу данных Neo4j и предоставляет инструменты MCP, веб-консоль и встроенного AI агента для анализа данных конфигурации.
Enable Claude Code to call Codex (GPT-5) asynchronously, filtering out thinking processes to save 95% context tokens.
A Claude Code plugin that turns Remotion from a motion graphics tool into a .
An MCP server that connects Claude Code to Google's Gemini 3.1, unlocking capabilities that complement Claude's strengths.
swagger-mcp is a tool that reads a Swagger 2.0 or OpenAPI 3.0 specification and dynamically generates MCP tools at runtime — one tool per API endpoint.
DEBUG-only iOS SDK that embeds an HTTP + WebSocket server in your app: browser console + MCP bridge for inspecting files, databases, network, logs, and the live screen. Zero third-party dependencies.
Agent Skills
Compatible with 13,000+ OpenClaw community skills — the largest AI agent skill ecosystem. One command to search and install.
Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, .
Elves is an open-source Agent Skill for handing planned development or research work to a separate worker without locking the run to one model provider.
Blueprint helps agents decide what to build, make focused changes, test them, get an independent review, and open pull requests.
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
(As usual, XKCD has a comic for this. Appropriately enough, the comic is out of date.)
A collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities.
Skills, rules, and validation hooks that teach AI coding agents to generate correct UdonSharp code
開源的 知識庫，分成 22 個主題類別。每個 skill 都是獨立的 Markdown 檔案（SKILL.md），遵循 Claude Agent Skills 規範，部分附帶純 Python 腳本做確定性計算。
仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。議事録・調査レポート・社内ガイド・リサーチメモ・スライド構成といった仕事の文書から、note・ブログ・エッセイまで扱います。
This guide is intended for anyone with zero or a small background in programming, AI, or machine learning who wants to become a strong AI engineer in 2026.
Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly. Instead of making language models reconstruct molecular structure from cryptic strings, MoleCode lets...