Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
This repository contains a complete tutorial on how to create an MCP (Modular Computational Platform) client in Python using FastAPI.
An MCP server that provides access to LLMs using the LlamaIndexTS library.
The ngrok alternative with .local domains, a scriptable CLI, and an MCP server for AI agents
Typed async Python clients + MCP server for Romania's ANAF web services: e-Factura, e-Transport, and public taxpayer lookups.
MCP server to extract contents from a PDF file
The purpose of the repo is to teach you how to make MCP servers. The target audience are non-technical with no real coding experience.
Open-source SAST engine that traces vulnerabilities across files and functions
The AI agentic designer — open-source React design system + MCP that lets Claude, Codex, Cursor & Gemini build production UI in minutes. No AI slop.
Shared MCP server for the Upvote.club Public API.
MCP server for flyonUI
The enterprise-grade TypeScript framework for building production-ready MCP servers. Decorators. Dependency Injection. Widgets. One framework to ship AI-native backends.
Agent Skills
Desktop-first workspace for managing AI coding agents through one React interface and explicit Web/mock and Tauri runtime boundaries.
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Please see https://fast-agent.ai for latest documentation.
发现真正适合你的高质量内容 —— BestBlogs 是 AI 驱动的私人阅读助手。
51 specialist AI agents for US healthcare administration. Installable prompts and skills for Claude Code, Codex, OpenCode, Cursor, Copilot, and other agentic coding tools.
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
Find the skills your coding agents load, see which agents can use each one, and count how often you use them
Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.
A complete agentic pipeline to kill a SaaS: pick a target, cut the 20% that matters, rebuild it on your boilerplate, ship it to production. One method = a suite of commands.
一套 的 UI/UX 咨询 Skill。它不是一个"特定审美的助手"，而是一个 ：
A reusable agent skills registry for Claude Code and Codex
German AI Text Humanizer · Claude Humanizer Deutsch · KI-Texte humanisieren Deutsch · Supports Claude Code and Codex · Von Martin Moeller · basiert auf den Wikipedia-Leitlinien Anzeichen für...