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
Your AI assistant now remembers everything. Forever. Across every conversation.
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
Norman MCP Server Your finances, inside your AI assistant. Norman connects your accounting, invoicing, and VAT filing directly to Claude, Cursor, and any MCP-compatible AI. https://mcp.norman.
Living Memory Architecture for Autonomous AI Agents — MCP server with typed connections, beliefs, decay, reconsolidation
The decision layer for personal AI. Local-first runtime where agents automate across GitHub, Slack, Gmail & 45+ services — but every risky action can stop for your yes, workers (agents) earn autonomy...
个人知识库 MCP 服务器 — 对本地文档建立索引，并提供一组飞书 API 工具，通过 MCP 协议供 AI 客户端访问。
douyin-mcp 让 AI 同时读懂你的抖音创作数据和视频内容 本地运行 · 音轨文案按需提取 · 数据可追溯 · 面向个人创作者的 MCP Server
Enhanced note taking for AI Agents with supervision.
Yet Another Frida MCP Server - Full-featured MCP server for Frida dynamic instrumentation
Chat with AI, run tasks on autopilot, and manage your projects — all from one tab.
Agent Browser eliminates the need to configure each MCP server in every client. Connect your clients once to Agent Browser, and it will manage all your Server-Sent Events (SSE) MCP servers for you.
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.
Agent Skills
A Claude Code / Hermes skill + voice app. You turn on, assistant is not normal assistant. Assistant is . The Eridian. From Andy Weir's Project Hail Mary.
A transferable, software-engineering methodology for AI coding agents —
Sumi — UX/UI design intelligence for Claude Code: 43 skills, 168 references, 37 commands, an anti-slop engine, and an auditable citation trail. Start with /sumi:start.
"你们搞大模型的就是码奸，你们已经害死前端兄弟了，还要害死后端兄弟……" ——某位对未来充满警惕的工程师
一个面试准备 Skill，帮你快速生成一份**的面试准备文档——含公司调研、JD 解读、定制自我介绍、STAR 项目预案、高频问题、反问清单、Gap 清单等 8 个章节。
A penetration testing skill built on Kali Linux for AI agents such as Claude Code, OpenClaw, and Hermes Agent. Currently includes 269 CLI tools across 14 categories.
这是一套专业的 Claude Skills，帮助开发者**源代码，而不只是"看懂"。基于认知科学研究，融合精细询问法、自我解释测试和应用迁移验证，确保深度学习而非产生流畅幻觉。
Robots have been around for years but have never been autonomous — someone has to drive them with a remote, and they've stopped at scripted demos.
21 款 可独立安装的视觉风格 Skill · 在线体验 · 交流群 · 授权说明
TinyScientist: A Lightweight Framework for Building Research Agents
把 skills/resume-master 整个目录复制到全局 skills 目录：
A multi-agent system for automated bioinformatics analysis workflows