Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama
WinDbg extension + Python MCP server. Lets MCP‑compatible clients (Cursor, Claude, VS Code + Cline/Roo) drive WinDbg with clean, validated commands. Kernel‑first; user‑mode works too.
Easy install scripts and user guide for Zotero MCP — connects your Zotero library to Claude and other AI assistants
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
- — MCP Protocol v2 (spec revision 2026-07-28, streamable HTTP) and experimental StrongDM API support are here — see the release notes.
Allow all your Claude Codes to message each other ad-hoc!
Run it before Claude Code, Cursor, Windsurf, Cline, OpenCode, or another agent trusts new code, tools, prompts, or dependencies.
This MCP server connects your AI agent to — Google's creative suite for image and video generation. Your agent can:
Tool names match exactly what each server exposes. Tool-call output passes through unchanged (text or JSON), so you can pipe, redirect, or parse with jq.
Desktop Extensions: One-click local MCP server installation in desktop apps
A simple NextJS MCP client with sensible keybindings
Intercept AI requests, track usage, inject MCP tools centrally
Agent Skills
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, slash commands, skills, hooks, subagents, agent teams, and MCP servers.
Cursor plugin specification and official plugins
Collection of Apify agent skills
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
-- Only 1.6% of Claude Code's codebase is AI decision logic. The other 98.4% is deterministic infrastructure -- permission gates, context management, tool routing, and recovery logic.
Open-Source Multi-Agent AI Assistant — Not Just Chat, an AI Team That Gets Things Done
10 design principles for building agent-ergonomic apps.
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.
审查 PR 中的 bug、风险改动、缺失测试和发布说明。
Nothing is more valuable than time and money. In a world of AI agents, that's speed and token spend. A well-designed CLI is muscle memory for an agent: no hunting through docs, no wrong turns, no...
Planby is a React based component for a quick implementation of Epg, schedules, live streaming, music events, timelines and many more ideas.
Hivemind turns your traces into reusable skills across agents