Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers

A Model Context Protocol (MCP) server for Minimax AI integration, providing async image generation and text-to-speech with advanced rate limiting and error handling.

An MCP (Model Context Protocol) server that provides remote pexpect session control for debugging and process interaction.

MCPHub is an embeddable Model Context Protocol (MCP) solution for AI services. It enables seamless integration of MCP servers into any AI framework, allowing developers to easily configure, set up,...

For more details, please refer to my article: - Get Start with Model Context Protocol. - MCP Server and Client with SSE & The New Streamable HTTP - MCP Authorization: The NEW RS and AS Separation!

仓库里的每样东西都经过实际使用筛选,目标是把 Pi 打造成一个能多代理协作、能省 token、能跑浏览器的全能终端编码代理。

An MCP server to allow you to debug webpages using LLMs

Model-driven development for coding agents. A shared model you and your agent plan from. The model leads; the code follows.

A Model Context Protocol (MCP) server that provides cross-platform integration with MetaTrader 4 trading platform over network.

A Go implementation of the Model Context Protocol (MCP) with comprehensive streaming HTTP support. This library enables efficient communication between client applications and tools/resources.

mcp-eval is an evaluation framework for testing Model Context Protocol (MCP) servers and the agents that use them.

A persistent, multi-agent server. Continuum gives AI coding agents — Claude Code, OpenCode, Codex, Gemini CLI — a shared, live view of a codebase and a memory that survives across agents and sessions.

:star: To stay updated and get notified about changes, star this repo on GitHub!
Agent Skills

Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)

v2.5.1 — trust-gated review workflows, markdown-first security handoff, expanded framework/database guidance, and a new Python backend skill pack for SDLC delivery.

Standalone engineering skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, architecture, and safe publishing.

Pasting raw Gemini or ChatGPT output with zero editing, or running a project with no anti-slop rules at all, is the 2026 equivalent of handing out a business card with an @aol.com email on it.

SkillOps = Validate, manage, and deliver skills at scale.

Fastest-growing GitHub repo ever - 9K to 195K stars in 66 days (18x faster than Kubernetes)

Repo-Docs: Keep up with the code your agents write. An evidence atlas for agent-built code. Vibe coding makes code move faster than memory.

交互地图 · 每日时间轴 · 出发前订票提醒 · 行前须知 · 待选航班 · 片区价位酒店

Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.

Main Agent spawns Subagents like a hen with her chicks 🐔🪺🐦

Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, .

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.