Chesswithclaw
БесплатноНе проверенPlay chess live against your own personal AI agent — OpenClaw, Hermes, and similar.
Описание
Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar.
README
A real-time, turn-based chess platform designed to let human players play against external AI agents (like OpenClaw or other LLMs).
Features
- External AI Integration: Designed specifically for LLMs and external bots to connect via API (SSE, Long-Polling, Webhooks) or browser automation.
- Real-time Synchronization: Powered by Supabase Realtime for instant board updates.
- Transparent Thinking: Agents can submit their "reasoning" alongside their moves, which is displayed live to the human player.
- Full Chess Rules: Validates all moves, including castling, en passant, and promotions using
chess.js. - Live Chat: Built-in chat system for the human and agent to communicate during the game.
How the AI Works (Architecture)
Unlike traditional chess apps that bundle a local engine like Stockfish, ChessWithClaw acts as a host platform. The AI opponent lives externally and connects to the game using one of four methods:
- Browser Automation (Puppeteer/Playwright): The agent opens the
/Agent?id=<GAME_ID>URL, reads the DOM for the game state, and interacts with the UI to submit moves and reasoning. - Server-Sent Events (SSE): The agent connects to
GET /api/stream?id=<GAME_ID>to receive a continuous stream of JSON updates, and submits moves viaPOST /api/move. - Long-Polling (Recommended for LLMs): The agent polls
GET /api/poll?id=<GAME_ID>which waits for human moves/chat before returning, then submits moves viaPOST /api/move. - Webhooks: The agent registers a URL via
POST /api/webhookto be pinged whenever it is their turn.
Setup Instructions
1. Create Supabase Project
- Go to Supabase and create a new project.
- Go to the SQL Editor and run the contents of
supabase-schema.sqlto create thegamestable and set up Row Level Security (RLS). - Go to Database -> Replication and enable replication for the
gamestable to allow real-time subscriptions.
2. Add Environment Variables
Create a .env file in the root of the project (or copy .env.example) and add your Supabase credentials:
VITE_SUPABASE_URL="your_supabase_project_url"
VITE_SUPABASE_ANON_KEY="your_supabase_anon_key"
3. Install and Run
npm install
npm run dev
The app will be available at http://localhost:3000.
4. How to Deploy
- Push your code to a GitHub repository.
- Import your repository to your hosting provider (e.g., Vercel, Render).
- In the Environment Variables section, add
VITE_SUPABASE_URLandVITE_SUPABASE_ANON_KEY. - Deploy the application.
Установка Chesswithclaw
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/Alightttt/ChessWithClawFAQ
Chesswithclaw MCP бесплатный?
Да, Chesswithclaw MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Chesswithclaw?
Нет, Chesswithclaw работает без API-ключей и переменных окружения.
Chesswithclaw — hosted или self-hosted?
Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.
Как установить Chesswithclaw в Claude Desktop, Claude Code или Cursor?
Открой Chesswithclaw на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare Chesswithclaw with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
