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 NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.
Interactive User Feedback MCP
a magical desktop app that lets you chat with local or remote LLMs, schedule hourly or daily tasks, all superpowered by MCP
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so...
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
the MPP (Machine Payments Protocol) 402 challenge is , as a card-free enrolment lane for agents holding a Tempo wallet.
MCP server SDK/example implemented entirely in bash — build a Model Context Protocol server with no runtime dependency beyond a POSIX shell.
Agents and MCP Orchestration with Langchain.js, LlamaIndex.TS, and Microsoft Agent Framework!
MCP Monitoring with eBPF
Solon-AI Java LLM(tool, skill) & RAG & MCP & Agent(ReAct, Team) Application development framework Restraint, efficiency and openness It is the same type of development framework as LangChain,...
Multi-engine MCP server, CLI, and local daemon for agent web search and content retrieval — skill-guided workflows, no API keys.
🚀 Universal SDK for building next-gen MCP servers
Agent Skills
· 通过 MCP 协议把万得金融数据接入 Claude / OpenClaw / Hermes 等 AI Agent，并一站式收录 wind 自家数据 + 社区分析工作流共 34 个金融 skill
CAD 自动化设计技能包 — 让 AI Agent 真正学会用 AutoCAD
A comprehensive Claude Code skill that enables Claude to extract, analyze, and reverse engineer iOS applications. It processes IPA files, .
上传一张图片，AI 分析后生成结构化 JSON + 平文本提示词，可用于还原/复刻该图片。
AI Skills for Everyone：人人都能用的开源 AI 技能库（⚠️ Alpha内测版）
Extended health check for Claude Code - runs /doctor, then audits your workspace against Anthropic's 6 then & now context-engineering shifts
Yi3D is a simple and easy-to-use 3D modeling application, available on Windows and Linux.
Architecture Decision Records as executable specifications for coding agents. An agent reads the ADR and implements the decision. A human reviews and approves.
A comprehensive UX and design strategy system for AI tools. 17 specialized skills and 6 agents that cover the full product design practice — from early strategy and research through experience...
Claude Skill that format Wechat articles for 微信公众号 (微信公众号文章排版，支持自定义样式)
Pressure-test research claims with falsifiable evidence plans, adversarial checks, frozen verifiers, and proof ledgers.
A Pi package that adds an interactive ask_user tool for collecting user decisions during an agent run.