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 that facilitates structured, progressive thinking through defined stages.
Enable your AI agents to read, analyze, and modify Figma designs.
We don't make AI smarter. We make it experienced. AI coding memory — the local-first memory + judgment layer for AI coding agents. Save up to 50%+ of AI tokens. Stop repeating yesterday's bug.
MCP server to access Garmin data
The local runtime, CLI bridge, SDK, drop-in adapters, and wallet/auth/signing layer are MIT and readable here, so you can verify what runs on your machine rather than trust a black box.
A simple CLI to run LLM prompt and implement MCP client.
🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️
A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Hashcat and more.
A MCP server implementation for hyperbrowser
The open-source tunnel that scales with you. Don't pay for idle time. Secure, Rust-fast, and Pay-as-you-go.
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses,...
A simple MCP server for Obsidian
Agent Skills
A framework for AI-First development with Claude Code and Codex. One methodology, two compatible runtimes.
A composable dev process for agentic coding harnesses, packaged as modular skills. Turbo has sibling editions for Claude Code and Codex.
Local-first Research OS for papers, workflows, experiments, channels, and automation.
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.
This is an project. These templates are designed to run on the OpenClaw platform — they use OpenClaw's agent system, workspace structure, session management, sessions_send for bot-to-bot...
Built from practice, not theory — calibrated against real deals including vLLM/Inferact ($150M @ $800M) and Hugging Face ($235M @ $4.5B).
Skills that translate your coding agent's output into plain language: honest reports, straight verdicts, steps you can follow. MIT.
End-to-End security platform for OpenClaw AI agents.
面向硬件产品的PCB方案设计 AI Agent。输入产品需求，输出可评审、可落地的PCB原理图的方案。
BenchFlow The universal environment framework — a benchmark is just a frozen environment.
High-performance personal AI assistant in C++17
: 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.