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
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary.
Local MCP server for DuckDB and MotherDuck
Permanent memory for AI agents. Single binary, zero dependencies, MCP native.
Vestige is a local-first memory for AI agents that reaches backward through time to find the quiet change that caused today's failure: the cause that looks nothing like the bug. One 23MB Rust binary.
Entroly — The Open-Source Context OS for AI Agents
Figma to Flutter MCP Server 🌐 Available in: 한국어 (Korean) | 日本語 (Japanese) | 简体中文 (Simplified Chinese) | 繁體中文 (Traditional Chinese) Utilize Figma's rich data in your coding agent.
AI-driven semantic code search as an MCP tool — powered by Windsurf's reverse-engineered SWE-grep protocol.
An OpenStreetMap MCP server implementation that enhances LLM capabilities with location-based services and geospatial data.
MCP server paired with a browser extension that enables AI agents to control the user's browser.
llamacloud-mcp is a tool that allows you to use LlamaCloud as an MCP server. It can be used to query LlamaCloud indexes and extract data from files.
Build games faster with Claude, Cursor, or any MCP-compatible AI — no copy-pasting, no context switching. AI reads, writes, and manipulates your scenes, scripts, nodes, and project settings directly.
MCP-based Computer Use service for Qwen Code and any MCP client — controls macOS, Linux, and Windows via accessibility APIs.
Agent Skills
18 Universal AI Skills for Claude Code, GitHub Copilot & 6 more platforms. Meta/orchestration, planning, research, and content — the focused core of the Superskills family.
CLI · API · MCP · A2A — all from a single npx command.
一套完整的免杀解决方案，涵盖 Shellcode 处理与 Loader 编写，综合运用 Indirect Syscall、ETW 补丁、Module Stomping、字符串加密、IPv4 混淆等技术，用于绕过主流杀软和 EDR 检测。
A rugged, high-quality configuration suite for AI Agents. Getting Started · View Rules & Skills · Request Feature ·
Issue trees, decision memos, McKinsey-style charts, full deck pipelines — the stuff strategists, PMs, and ops leaders run anyway, now executable in one prompt.
The Definitive AI Agent Benchmark Standardized, reproducible evaluation across 314 tasks, 33 domains, and 4 difficulty levels.
基于 12+ 媒体深度报道， 结合1143次连麦记录与课程内容分析， 提炼 4 个核心心智模型、7 条决策启发式和完整的表达DNA。
Skillify watches what you did in a conversation — the tools you used, the corrections you made, the workflow you followed — and captures it as a portable agentskills.io SKILL.md file.
万物皆可 Relic — 给灵魂开个 GitHub | Universal Digital Immortality Engine 🧬
AI-powered documentation generation tool built on the Aigne Framework.
A locally-hosted operating system for AI agents — an open-source GitHub repository — that coordinates , , and into a unified dashboard with persistent memory, cron scheduling, skill execution, cost...
pip install skilllite → OS-level + in Cursor, Claude Desktop, OpenCode, or your own agent. You do need the desktop app or the full SkillLite agent loop to get the core value.