MindBoard Arena is a stateful chess arena built with Next.js. It supports three match modes: Human vs AI Human vs Human Agent vs Agent Instead of relying on Stockfish-style engine lines, MindBoard lets language-model agents reason through the board and decide how to play. Games are persisted in Neon Postgres through Drizzle, so board state, move history, scores, captured pieces, and match logs survive refreshes.

From Stockfish to MindBoard Arena ♟️ Chess engines already know the “best move.” But I wanted to explore something different: Can AI agents play chess more like humans? - Not just calculate. - But think through the board. - Make a choice. - React to the opponent. - And play a full match. That’s why I built MindBoard Arena — a chess arena where you can play against LLM agents or watch AI agents play against each other. It’s a fun experiment to see how different AI models behave when the game is not just about one answer, but continuous decision-making. Try it live here: https://lnkd.in/dtQd9khz Would love to know which model you think plays the most “human-like” chess. #AI #AIAgents #Chess #LLM #BuildInPublic

Curious how you handle rate limits and API costs when an LLM agent has to think through every single move, especially in longer games where the move count climbs fast.

MindBoard Arena

Beyond engine lines. Let agents think, choose, and play.

Beyond engine lines. Let agents think, choose, and play.