Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result
No Microsoft Graph API, no Entra app registration, no OAuth tokens — just your local Outlook and the authentication you already have.
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
Please see the updated mcpb format Claude Desktop Extension
The cognitive memory layer for AI agents.
A complete, driver-based RAG (Retrieval-Augmented Generation) pipeline for Laravel. Built on Prism PHP for provider-agnostic LLM and embedding support.
Scan your dev machine for AI agents, MCP servers, IDE extensions, suspicious files, and risky package-manager configs — in seconds.
A single-binary MCP server that connects Claude Desktop and Claude Code to Microsoft Outlook via the Microsoft Graph API.
Agent Skills
Everything you need to know about OpenCode — from your first prompt to custom agents, skills, plugins, and MCP integrations.
Blueprint helps agents decide what to build, make focused changes, test them, get an independent review, and open pull requests.
Part of the NVIDIA Cosmos project family — the training and serving framework repository.
Guides and production-ready commands for Claude Code: skills, subagents, hooks, memory, custom commands, and conversation-history tooling.
The open-source desktop AI agent that gets work done — an agent that plans and self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in a single self-hostable stack.
PavedPath Code（代码版）is a reusable Skill for finding proven implementation paths from GitHub and open-source evidence, then adapting them to local software engineering problems.
AI agents like Claude Code ship features fast. AIDD Framework keeps them working, secure, and maintainable.
A collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities.
Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
開源的 知識庫，分成 22 個主題類別。每個 skill 都是獨立的 Markdown 檔案（SKILL.md），遵循 Claude Agent Skills 規範，部分附帶純 Python 腳本做確定性計算。
A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...