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
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,...
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.
Open-source adversary emulation for AI agents, LLM apps, and MCP servers. Test your AI like a real attacker would — from your CLI, your IDE, or a browser extension that anyone on your team can use.
Multi-Agent + Automation: Workflows, Automation, Self-Improving Agents
Docs Quickstart // Join us on Slack
Stop managing DevOps. Ship more, stress less.
The web data API for AI agents — search, scrape, map, and crawl any site into clean markdown or JSON .
MCP Playbooks for AI agents
Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.
· · · · · academic foundation (KDD 2024, ICLR 2026) · runs in CI/CD, as a Python library, an MCP server, or an Astro integration
Your ssh config, synced with your cloud.
Zero config. Zero dependencies. Under 10 seconds.
Agent Skills
The #1 Kubernetes skill for Claude Code and Codex, measured by GitHub stars.
Elves is an open-source Agent Skill for handing planned development or research work to a separate worker without locking the run to one model provider.
An that runs end to end on the Atlas Cloud API + local ffmpeg, usable by any coding agent (Claude Code, Codex, etc.). You give it a one-line topic; it gives you an mp4.
The #1 Terraform skill for Claude Code and Codex, measured by GitHub stars.
The map is not the territory. Your prompt is a map; the codebase and the real world are the territory.
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
LeetCode Helper is a Codex skill for solving LeetCode-style coding interview problems with optimized solutions and detailed explanations.
The open-source desktop AI agent that gets work done — an agent that plans and self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in a single self-hostable stack.
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.
The skills I actually use to build software with coding agents. Straight out of my .claude/skills/ folder.
A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...
一句话：输入一个基金代码，Agent 把基金经理 8 年的每一笔买卖翻出来，拿 12 个月后的真实走势逐笔验对错，最后吐出一份 700KB 的单文件交互报告——K 线战役回放、买卖点验尸、独立性审判、造神检测，全都有。