Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
A collection of Power Platform custom connectors, MCP servers, and connector code samples for Microsoft Graph APIs, document collaboration, and enterprise services.
The fastest BM25 scoring engine: 2,300x faster than BM25S. 28K QPS on 8.8M docs. 5 BM25 variants (Robertson, Lucene, ATIRE, BM25L, BM25+). Memory-mapped persistence, BMW pruning, streaming indexing.
Dieser Server implementiert das Model Context Protocol (MCP), um deutschen Gesetzestexte für LLMs (Large Language Models) bereitzustellen.
LLM Gateway to call 100+ LLM APIs in OpenAI format with MCP supported.
Trusted Model Context Protocol (Trusted MCP)
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Yet another minimal MCP server for Unity
one go multi-agent system like manus using any MCP you want with configuration // 一个go语言编写的类似manus的多智能体系统，可以通过配置连接任何你想使用的MCP组件
MCP bridge system optimized for Xiaozhi AI integration
A Model Context Protocol (MCP) server for interacting with the Hetzner Cloud API. This server allows language models to manage Hetzner Cloud resources through structured functions.
FastMCP for Google's langextract library
This project demonstrates how to build a multi-agent system using Agent-to-Agent (A2A) communication with the Model Context Protocol (MCP).
Agent Skills
Collection of components and sections specifically designed for creating landing pages with Nuxt 4 and Nuxt UI.
CLI to manage emails
Clone of nanoclaw in Elixir
Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
Shared guardrails, skills, and bootstrap scripts for AI coding agents
Turn noisy command output into a short, actionable first pass for coding agents.
Unofficial Python CLI for Google Flow. Drive Veo (image-to-video, text-to-video) and Imagen (text-to-image) from your terminal: scripted, batched, pipeline-ready.
Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth.
Vendor-neutral, persistent project context for AI coding agents. Shared state lives under docs/context/, stays reviewable in Git, and survives chat resets, compaction, and switching agents (Claude...
AI code review that lands on the PR, not in your terminal — GitHub, GitLab, Bitbucket. Learns each repo's conventions: 1 review, 1 fix commit, replies in thread.