gitwtfhub

wtf is maia-chess?

qz267/maia-chess — explained in plain English

Analysis updated 2026-07-18 · repo last pushed 2021-01-14

Audience · researcherComplexity · 3/5DormantSetup · moderate

TL;DR

Maia is a chess engine trained on millions of real Lichess games to play like a human at a chosen skill level, instead of playing at inhuman perfection like traditional engines.

Mindmap

mindmap
  root((repo))
    What it does
      Mimics human play
      Plays at set skill level
      Trained on real games
    Tech stack
      Neural network
      Lichess data
    Use cases
      Practice at your level
      Study AI alignment
      Power teaching tools
    Audience
      Chess students
      AI researchers
    Availability
      Play on Lichess
      Download trained models

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Play against a chess engine that makes human-like mistakes at your own skill level instead of an unbeatable AI.

REASON 2

Study how an AI model learns to mimic human decision-making, as a case study in AI alignment research.

REASON 3

Download the pre-trained Maia models to power a teaching tool or chess trainer app.

REASON 4

Train your own human-like chess model from a different set of games using the included training code.

What's in the stack?

Neural NetworkPython

How it stacks up

qz267/maia-chess0verflowme/alarm-clock0verflowme/seclists
Language—CSS—
Last pushed2021-01-142022-10-032020-05-03
MaintenanceDormantDormantDormant
Setup difficultymoderateeasyeasy
Complexity3/52/51/5
Audienceresearchervibe coderops devops

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · moderate Time to first run · 1h+

Training your own models requires a dataset of games and machine learning setup, though pre-trained models are ready to download.

Yoink these prompts

Prompt 1
Explain how Maia's neural network learned to mimic human chess players at different skill levels.
Prompt 2
Show me how to download and run one of Maia's pre-trained models to analyze a chess position.
Prompt 3
Walk me through training my own Maia-style model using a different dataset of chess games.
Prompt 4
How does Maia's approach to blunder prediction differ from a traditional chess engine's evaluation?

Frequently asked questions

wtf is maia-chess?

Maia is a chess engine trained on millions of real Lichess games to play like a human at a chosen skill level, instead of playing at inhuman perfection like traditional engines.

Is maia-chess actively maintained?

Dormant — no commits in 2+ years (last push 2021-01-14).

How hard is maia-chess to set up?

Setup difficulty is rated moderate, with roughly 1h+ to a first successful run.

Who is maia-chess for?

Mainly researcher.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.

Other repos in this lane