Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
tRPC to MCP package
Today, we are moving beyond standard chatbots. In this hands-on lab, you will build a deterministic, multi-reasoning system using Google's Agent Development Kit (ADK) and the Model Context Protocol...
A collection of Power Platform custom connectors, MCP servers, and connector code samples for Microsoft Graph APIs, document collaboration, and enterprise services.
MCP bridge system optimized for Xiaozhi AI integration
Runtime intelligence system that makes MCP servers debuggable, testable, and safe to run in production.
gollem provides: - to query prompt to Large Language Model (LLM) services - Generate / Stream: Generate text content from prompt (with per-call option overrides) - GenerateEmbedding: Generate...
VASPilot is an open-source platform that fully automates VASP workflows via a multi-agent architecture built on the CrewAI framework and a standardized Model Context Protocol (MCP).
Expect rapid changes and occasional rough edges.
Enhance your GitHub Copilot experience with comprehensive instructions, prompts, chat modes, and configurations.
Levante is a cross-platform desktop app (Windows, macOS, Linux) that brings powerful AI tools closer to everyone — not just technical users.
Production-grade multi-agent orchestration engine. Compose agentic workflows from a pluggable catalog of Agents, LLMs, tools, and retrievers.
kiro-discord-bot connects Discord channels and threads to ACP-compatible coding agents over stdio. Kiro CLI is the default engine, while OMP can be enabled as an optional replacement behind the same...
Agent Skills
This repository contains hands-on tutorials for learning LangChain, LangGraph, and Deep Agents, organized into two learning tracks:
A growing collection of design skills for AI coding tools — Claude Code, Cursor, Codex, Windsurf, and anything else that reads a markdown rules file.
Honey (I Shrunk the AI) by GreenPT is a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — making agents emit less code and less prose without losing correctness.
A reusable skeleton for an built on Hermes: a fleet of agents that items from sources, them, them against a rubric, them in parallel, each to a fulfillment path, pauses at , then — all coordinated on...
A Claude Code skill for maintaining and optimizing OpenClaw workspace files — the markdown files that form an AI agent's soul, memory, and operating procedures.
A framework for AI-First development with Claude Code and Codex. One methodology, two compatible runtimes.
Fourth girlfriend voting in progress - please vote on Issues.
终端里起多个会话并行干活、互相通信；长任务跑着的时候人走开了，也能从微信/企微把它喊回来。
基于 Hermes 改造的轻量级 AI 助手框架，可以快速打造商用 SaaS 平台，支持多租户隔离部署、多平台渠道接入、工具调用、定时任务和 Web 实时通信。
A design skill for building never-cheap, high-craft web interfaces — both brand surfaces and product UI.
A file-backed, spec-driven AI coding workflow framework for building real software while staying in control.
: Claude Opus 5 (claude-opus-5) / Claude Opus 4.6 (earlier chapters) : Claude Code + OpenClaw + OpenCode : 2026-08-02 : v2026.3.9 (v2026.3.8-170-g665f67726) : https://github.