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

This repository contains TypeScript packages for integrating Ory authentication and access control with the Model Context Protocol (MCP).

将本地 MCP 服务器无缝接入各大网页版 AI 助手的浏览器扩展 本项目由 OPENCODE + Claude Opus 4.6 完成

Bot to Spam messages on YouTube Live Stream Chat with an integrated MCP Server and a Realtime Dashboard

A Python-Based MCP Server for Hopper Disassembler

This is an MCP server implemented using the RMCP (Rust Model Context Protocol) library for operating Containerd.

Learn how to implement MCP client with SwiftUI and Anthropic API

A centralized gateway for managing and connecting to multiple MCP (Model Context Protocol) servers. Provides secure, scalable access to MCP servers with SSO authentication, session isolation, and...

一个基于 MCP(Model Context Protocol)协议的智能宠物伴侣应用,通过语音识别和自然语言处理技术,为宠物主人提供实时互动和服务。该应用是一个 MCP-Client 应用,可以自主无限搭配 MCP-Server 实现需求。

Anthropic’s Model Context Protocol implementation for Oat++

A simple Model Context Protocol (MCP) server for Mesh.

A comprehensive platform for managing and proxying Model Context Protocol (MCP) servers, providing scalable AI service orchestration across multiple microservices.

A crate for making MCP (Model Context Protocol) compatible programs with rust
Agent Skills

This repository provides a collection of composable Dockerfiles and build scripts for deploying and running software, full applications, and select demonstrators on AMD Ryzen AI hardware.

🧬 Darwinia Give your AI agent the power to evolve its own trading strategies. Trading agents that discover strategies through Darwinian selection and adversarial self-play — not human-written rules.

Why use many token when few token do trick?

小提示:导入数据时**,尽量不要用 JSON——多数微信导出工具的 JSON 是给 LLM 微调用的格式,没有时间戳,跑不出 K 线。详见 输入格式。

—— 一套可被任意 AI agent(Claude / GPT / Cursor…)使用的**。

面向 AI Agents 的安全、可持久化沙箱执行平台(Secure, Persistent Execution Platform for AI Agents)

Your future self will thank you. Or blame you. It depends on the diff.

TL;DR: Thea brings coding agents to the physical world.

A Claude Code plugin that audits your mobile app against store review policies — the store rejects it.

A grab-bag of experimental transformer kernels and utilities (mostly PyTorch + Triton).

10 agentes (8 de núcleo, Selina si hay frontend y Lucius bajo demanda), catálogo de 11 skills de proceso, memoria persistente de decisiones por proyecto, 6 flujos de trabajo con quality gates...
Most research-idea workflows fail in one of three ways: