Announcing maiachess.com

For the last several years, our group has been building Maia: chess AI designed to think and play like us, not like a machine. Today, we're excited to share the official Maia Chess platform: maiachess.com.

Maia Chess is built around a simple idea: chess is richer when you can see it through a human lens—not just what the engine move is, but which moves real players see, which mistakes they’re drawn toward, and how that changes the way you play, analyze, improve, and have fun with the game.

What is Maia?

Maia is a neural network chess engine trained to play like a human. Unlike traditional engines that play robotically, Maia naturally plays moves that a person would make. Trained on millions of human games, Maia has human chess intuition and decision-making style. And Maia is more than just a bot: it's a full chess AI with human context that supports learning, training, and fun features.

Meet Maia-3: our brand new model that plays at any level from 600 to 2600

On maiachess.com, we're launching Maia-3, our completely re-architected model that is the most human-like model in the world, supports any rating from 600 to 2600 Lichess blitz, and has a ton of cool features. Whether you're just starting out or you're a titled player, Maia-3 can match your level with realistic play. You can configure time controls (bullet through unlimited) and choose "Human-like" thinking time, where Maia takes its time like a person would. The games feel different from Stockfish: Maia plays natural-looking moves, occasionally misses a tactic you'd expect a player at that level to miss, and punishes you in the ways a human opponent would. It's practice that transfers to your real games.

Analyze games with Maia

This is personally my favourite feature. You can analyze any game—your games on the platform, your Lichess games, famous historical games, or any game or position you want—with a dual Maia / Stockfish analysis view. By augmenting traditional engine analysis with Maia's human understanding, you get real-world context in every position. In Maia analysis, you see:

• What Maia predicts people at different rating levels would actually play, and with what probability
• What Stockfish thinks is objectively best
• A "Moves by Rating" chart showing how move choices shift across the skill spectrum, so you see what human progress looks like in every single position
• Blunder detection that understands which mistakes are natural and which are surprising for your level
• Position danger analysis that measures whether people at your level navigate this position well, or if they tend to make mistakes
• A human evaluation bar that tells you how good the position is from a human point of view, and at a given rating level. How likely is a 1200-rated player to win this position, or an 1800-rated player, or a 2500-rated player?

This gives you something we didn't have before: chess AI with human context. Your move might have been objectively second-best but completely natural for your rating. Another move might be the engine's top choice but almost no human below 2000 would find it. Some mistakes you make would even be played by GMs—but others you shouldn't be missing at your level (so you should probably work on those first). Maia's analysis lets you see chess through the lens of human play, and understand not just what's best, but what's realistic, where you're likely to stumble, what players slightly above your rating are doing differently, and what you need to change to get to the next level.

Puzzles

Maia's puzzle trainer isn't a standard tactics set. The puzzles are curated using Maia's understanding of human play, targeting the specific positions where players at your level actually go wrong. Each puzzle shows data on how players of different ratings approach the position, so you can see not just the solution but why wrong answers are tempting.

Drill with Maia

Pick any set of openings, endgames, or custom positions, choose a side, select a Maia opponent rating, and drill. It's a great way of getting customized practice with realistic, tailored opposition.

The difference from practicing against a traditional engine: Maia responds the way a real opponent at your target rating would. If 1200-rated players rarely play the critical theoretical move in a given line, Maia won't either. You're training for what you'll actually face across the board, not fighting alien engine responses.

Hand & Brain

Play hand & brain, a collaborative chess variant where you team up with Maia. Be the "Hand" (choosing which square to move to) while Maia is the "Brain" (selecting which piece), or vice versa. It's a fun and surprisingly instructive way to play. You need to reason about how your human-like partner is thinking to win the game.

Bot or Not: The Chess Turing Test

Can you tell human from machine in chess? We show you games and you decide. Are you a human chess whisperer, or are you stumped by the engines?

Broadcasts

Follow live tournament broadcasts and live Lichess games with Maia's real-time analysis overlay. See the critical moments from a human perspective alongside the engine evaluation. Currently broadcasting events include the FIDE Candidates 2026 tournament!

Leaderboards

Every game mode (play, puzzles, Bot or Not, etc.) has its own leaderboard, so you can see where you stack up.

Free and open source

Maia Chess is an academic research project from the University of Toronto CSSLab. The platform is completely free. You sign in with your Lichess account and away you go. Our research on Maia has been published at top-tier AI conferences such as NeurIPS, TMLR, and KDD, and the Maia code is fully open source.

Big thanks to Lichess.org

Thank you to Lichess for providing not only the data Maia was trained on but for fostering an open and thriving global community of chess fans.

Come try it!

Head to maiachess.com, sign in with your Lichess account, and experience chess from a different perspective. Join our Discord to connect with our community. We'd love to hear what you think, what you enjoy, and what you want us to build next!

— Ashton Anderson and the Maia Chess team