CSSLab/maia-chess
Maia is a human-like neural network chess engine trained on millions of human games.
Provides skill-stratified models (ELO 1100–1900) that predict average human moves rather than optimal play, implemented as Leela Chess Zero neural network weights requiring minimal search (1 node). Includes training pipelines to create custom models from PGN game files, blunder prediction capabilities, and playable bots integrated with Lichess; models are evaluated on move prediction accuracy across skill levels rather than engine strength.
1,140 stars. No commits in the last 6 months.
Stars
1,140
Forks
140
Language
Python
License
GPL-3.0
Category
Last pushed
Jun 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CSSLab/maia-chess"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
LeelaChessZero/lc0
Open source neural network chess engine with GPU acceleration and broad hardware support.
official-stockfish/nnue-pytorch
Stockfish NNUE (Chess evaluation) trainer in Pytorch
QueensGambit/CrazyAra
A Deep Learning UCI-Chess Variant Engine written in C++ & Python :parrot:
bagaturchess/Bagatur
Java Chess Engine (UCI compatible)
bcorfman/raven-checkers
An open-source checkers game with a computer-based AI, written with Python and Tkinter.