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
MCP configuration to connect AI agent to a Linux machine.
Auto Browser is an MCP-native browser control plane for authorized workflows. It gives MCP clients, LLM agents, and operators a shared Playwright browser with human takeover, reusable auth profiles,...
Local code intelligence MCP server and CLI for AI coding agents
Casbin AI & MCP security gateway for HTTP, online demo: https://door.caswaf.com
All in one vscode plugin for mcp developer
Early WebMCP proposal / implementation - since evolved and worked on by much more capable folks that develop the web: https://github.com/webmachinelearning/webmcp
NEW · Agent in the loop — Using AI to assess the risk of one-off operations. Read more → One Gateway Between Your Team and Your Infrastructure. hoop.
MCP server wrapper for OpenAI Codex CLI that enables Claude Code to leverage Codex's AI capabilities directly.
Real websites for your coding agent to learn design from, searchable over MCP.
Cross-session context persistence for AI coding. A file convention, a CLI, an MCP server, and Claude Code/Codex skills that together turn every coding session into a building block instead of a reset.
Diagram generation for understanding codebases and system architecture using Nano Banana Pro.
Agentic Capabilities and Package Manager
Agent Skills
micro-agent orchestrator for local agents
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Curated guidance for AI assistants building MapLibre applications — covering ecosystem and open-source best practices.
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot,...
Public repository for Agent Skills
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills...
Generate draw.io diagrams from natural language — 11 presets (UML, SysML/MBSE, BPMN, network, C4…), 39 tools: codebase/CI/infra-to-diagram, image→editable diagram, Databricks product icons, mind...
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
adds freshness decay (time-weighted memory), claim verification (verify_file_path MCP tool), 12 MCP tools (was 8), and 30+ bug fixes.
Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done.
首先感谢 Andrej Karpathy 的《LLM Wiki》原文。这个项目直接受那篇 idea file 启发而来。