Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Give Claude on the (claude.ai) and read/edit access to files and a whitelisted shell on your local machine, over HTTPS via Tailscale Funnel, gated by OAuth 2.1. No desktop app, no device install.
Sovereign, encrypted, portable memory for AI agents.
Your digital developer twin — because "explain our setup again" gets old fast.
A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.
OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.
An MCP server that connects to a Swagger specification and helps an AI to build all the required models to generate a MCP server for that service.
A Stdio MCP server which proxies an SSE MCP server.
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
MCP server to enable an LLM to do basic static triage of a PE.
MCP server to extract contents from a PDF file
Shared MCP server for the Upvote.club Public API.
The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
Agent Skills
Mac OS X utility to un-archive .webarchive files (like when saving from Safari)
A practical skill pack for DevOps work in Claude Code and Codex desktop.
Agent-readable design systems for product UI.
~100 skills for Claude Code — meeting pipelines, research, image generation, TDD, publishing, personal analytics, and Claude Code ops. Each skill is a self-contained folder with a SKILL.
🌊 基于复杂自适应系统（CAS）理论的 Agent-Native 通用人类社会行为预测引擎
产品经理最耗时的工作不是写 PRD，是**——想清楚该有哪些章节、每个章节该写什么、哪些维度容易遗漏。这个过程往往占了写文档时间的一半以上。
专为 AI CLI 工具（Claude Code / Gemini CLI）设计的模块化渗透测试技能集合。
A small, portable collection of Hermes Agent skills for operating Hermes through Buzz: connecting a remote Hermes gateway to a Buzz community and delivering local media as native Buzz attachments.
The official Vast.ai Python package — provides both the CLI and SDK for managing Vast.ai GPU cloud resources, plus a serverless client for endpoint inference.
A definitive guide to building robust, efficient, and maintainable Go applications—without the enterprise baggage.
This skill makes an AI agent write in a plain style. The full rules are in SKILL.md.
A minimal implementation of Recursive Language Models (RLM) using Claude Code as the scaffold. Implemented by Brainqub3.