Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers

AI 端到端开发 Cocos Creator 3.8 游戏 — 42 个 MCP 工具 + Claude / Codex / Cursor Skill

Total recall for your terminal. Shared memory for your AI agents.

combining Claude Code monitoring, Claude Code config management, hooks, agents, and MCP servers in a single 5.8MB binary. 89x faster startup with SQLite cache, 492 tests, 0 clippy warnings.

Your digital developer twin — because "explain our setup again" gets old fast.

Sovereign, encrypted, portable memory for AI agents.

IGraph 把代码仓库解析为「符号节点 + 调用关系边」的知识图谱,叠加 LLM 语义摘要与向量索引,通过双通道(Dense + FTS5)RRF 融合检索对外服务。支持挂载 PRD / DB Schema 等多模态资源建立跨模态关联,内置 MCP Server 可直接接入 Cursor / Claude Code 等 AI 助手。

MCP server for Things 3 via Things Cloud API

🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama

A simple NextJS MCP client with sensible keybindings

This project is a for automating and managing interactions on a Facebook Page using the Facebook Graph API.

CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.

A progressive AI Agent Harness tutorial written in Rust.
Agent Skills

A catalog of installable skills for AI coding agents: Claude Code, Codex, Antigravity, and Grok.

Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic

qmd-prover is an add-on for your AI coding assistant — or — that helps it write and check real mathematics.

👩🚒 Good content deserves good paper.

"一器而工聚焉者,车为多。" ——《考工记》 两千年前,造一辆马车是最复杂的系统工程:**承载乘者,辕定方向,辐传动力,軎辖为约束——每个构件各司其职,合而为一,车方能行。 今天,构建一个 AI Agent 亦是如此:对话循环为**,工具系统为**,权限管线为**,而将这一切承载于其上、使智能体真正运转的运行时框架—— Agent Harness——正是那个**。

Fork-and-go template for a private team skills marketplace usable from Claude Code and Codex CLI

GEO-first SEO skill for Claude Code. Comprehensive AI search optimization for any website — citability scoring, AI crawler analysis, brand authority, schema markup, platform-specific optimization,...

该技能可以让龙虾对任何事实进行多维度核验,从不同学科视角深入分析和研究问题,往往可以给出让人惊艳的输出结果。

Karpathy's LLM coding guidelines merged with Ponytail's laziness ladder, think before coding, climb the simplicity ladder, touch only what you must.

Claude Code skills and sub-agents for .NET Developers

The LLM router built for autonomous agents

Turn any codebase into an AGENTS.md playbook AI coding agents can actually follow.