Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

https://github.com/user-attachments/assets/2430b854-168b-4a9a-af2e-489e5efa7543

Stop managing DevOps. Ship more, stress less.

Multi-Agent + Automation: Workflows, Automation, Self-Improving Agents

EdgeEver is an open-source, self-hosted, Cloudflare-native notes workspace. It keeps the classic Evernote-style three-pane experience while providing a clear data model, REST API, OpenAPI schema,...

One command. Full visibility. Read-only.

基于 FastAPI + LangChain + OpenAI 构建的小红书内容挖掘与自动生成系统。支持从爬取竞品数据、分析爆款规律、AI 生成文案与配图,到一键发布至小红书的完整闭环。

小智AI客户端,目前主要用于MCP的对接

While other amazing Figma MCP servers like Figma-Context-MCP exist, one issues is the API limiting for free users.

Local-first memory, visualized. 3,800+ entities and 41,000+ connections, captured automatically as you work.

一个本地优先的 AI 知识库系统(RAG),用于将本地文档接入向量检索与大模型对话流程。项目提供 Web UI,支持知识库管理、文档上传、检索增强问答、聊天记录持久化,以及基于 Ollama 或 OpenAI 兼容接口的模型接入。

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool...

This is a dnSpy MCPServer Extension for the use of automated AI .NET reverse engineering The \dnSpy\Extensions\Examples\AgentSmithers dnSpy MCPServer.
Agent Skills

Turn one photograph into an editorial composition built from the original photo, an abstract memory panel, and a poetic English title.

The Retained Mode JavaScript framework that refuels your UI projects, across web, native, and embedded, with built-in HMR support.

A lightweight Python agent for one trusted user and one running instance.

A photograph carries more than its visible subjects. It holds intervals, direction, visual weight, color memory, and relationships that may not yet have found their final form.

帧棒是面向《三角洲行动》玩家的 Windows 画面与帧率优化工具(非官方个人项目,游戏名称仅用于说明适配用途),支持 AI Agent 调用 Skill,完成系统检测、优化执行与一键还原。

A single Go binary inspired by exe.dev: create persistent Linux VMs on macOS, Linux or Windows, vibecode inside them with models from Ollama Cloud, and publish any VM port to a real HTTPS subdomain...

This repo contains supplementary materials for the talk "Introduction to the Omniverse and Isaac Platform for Robotics".

Your modular, always-on-top desktop utility sidebar. A multi-threaded creative assistant that lives on the edge of your screen.

zotero-literature-visualizer 是面向 Codex 的学术文献工作流 skill。它可从研究主题或已有 Zotero 文献库出发,完成文献检索、期刊质量核查、已有本地 PDF 的全文整理、Zotero 条目整理、中英文研究摘要,以及交互式文献 dashboard 的生成。

它扣掉的只有两件事:固定 IP 形象和固定配色。使用者只需要填写自己的 IP 角色公式和品牌配色,就可以把文章、知识点、教程内容转成一套带个人风格的配图 Prompt。

面向全国大学生数学建模竞赛(CUMCM)的完整建模论文分步审核工作流技能,兼容 Codex、Claude Code 等支持 Agent Skills 规范的 Agent。

Stop your AI agent from failing halfway through a skill. One library for all your agent skills — with a pre-flight check built in.