Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
🇨🇳 → 优先选择 🚀 🌍 → 选择 🌐 📱 → 所有链接都支持手机浏览器直接下载
Integrate yt-dlp with Claude, Dive, and other MCP-compatible AI systems. Download videos, extract metadata, get transcripts, and more — all through natural language.
An MCP server that wraps around Google's Lighthouse tool to help measure various performance metrics for web pages.
, , and all run on stock GitHub-hosted runners (cloud CI) — no docker image, no self-hosted runner. E2E and Conformance run against (currently build 2026.1.
An open source Model Context Protocol (MCP) server and command-line tool that helps your AI coding assistants quickly create baseline IAM policies that you can refine as your application evolves, so...
A Model Context Protocol (MCP) server that provides Ant Design component documentation to large language models (LLMs) like Claude.
MemoryMesh is a knowledge graph server designed for AI models, with a focus on text-based RPGs and interactive storytelling.
Vibe coding should have human in the loop! interactive-mcp: Local, cross-platform MCP server for interact with your AI Agent
An Android application that runs as an , enabling AI models to remotely using accessibility services and screenshot capture.
한국 공공 데이터 포털(data.go.kr) API를 Model Context Protocol (MCP) 서버로 제공하는 프로젝트입니다.
A Model Context Protocol (MCP) server providing comprehensive access to Google Search Console data with enhanced analytics capabilities.
MARM: Local-First Persistent Multi-Agent Memory Layer for MCP Clients v2.22.0
Agent Skills
Compatible with 13,000+ OpenClaw community skills — the largest AI agent skill ecosystem. One command to search and install.
Main Agent spawns Subagents like a hen with her chicks 🐔🪺🐦
An EasyEDA Pro API skill package for AI coding tools such as Claude Code, OpenCode, QwenCode, and any other tool that supports the Agent Skills standard.
The open-source desktop AI agent that gets work done — an agent that plans and self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in a single self-hostable stack.
agnix Lint agent configurations before they break your workflow
Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.
A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...
一句话：输入一个基金代码，Agent 把基金经理 8 年的每一笔买卖翻出来，拿 12 个月后的真实走势逐笔验对错，最后吐出一份 700KB 的单文件交互报告——K 线战役回放、买卖点验尸、独立性审判、造神检测，全都有。
Local-first harness for agent-built codebases. Humans steer, agents execute, maestro is the substrate.
ProductSpec is the open standard for product intent. It acts as a Product Harness for AI-native software work: what to build, what not to build, how to prove completion, and when intent changes.
AI coding agents are great at Python. They hallucinate in Spring Boot.
- Manage Claude Code, OpenAI Codex, Google Gemini, OpenCode, and custom AI agents from one powerful command-line interface.