Alternatives

Products that do what Maia, a human-like neural network chess engine does

1. 1AA
   Aim and Shoot – A game where your opponents are neural networks▲118

   2019 · github.com

2. 2OS
   Open-sourced my Java chess AI high school project▲51

   2013 · github.com

3. 3PG
   Play Go Against a Deep Neural Network▲77

   2015 · chrisc36.github.io

4. 4RC
   R-cade, a simple arcade game engine for Racket▲205

   2020 · github.com

5. 5RN
   Recurrent neural net plays 'neural slime volleyball' in JavaScript▲147

   2015 · otoro.net

6. 6PR
   Play rock paper and scissors against a untrained neural network▲101

   2019 · github.com

7. 7AP
   AI Planning for Starcraft▲78

   2015 · github.com

8. 8
   Sonnet▲134

   A new library for constructing neural networks from DeepMind

   2017

9. 9NA
   Numerai – A global AI tournament to predict the stock market▲68

   2015 · numer.ai

10. 10NN
    Neural Network Evolution Playground with Backprop NEAT▲73

    2016 · blog.otoro.net

11. 11AP
    A perceptron with stochastic gradient descent in Go▲94

    2017 · github.com

12. 12MA
    Monsiv – A lightweight alternative to Chess▲17

    2018 · monsiv.com

13. 13AV
    A Visual and Interactive Guide to the Basics of Neural Networks▲63

    2016 · jalammar.github.io

14. 14OA
    Orca – AI Game Engine▲9

    2025 · github.com

15. 15TT
    Tic Tac Toe – Creating Unbeatable AI▲6

    2019 · towardsdatascience.com

16. 16MA
    Mind, a flexible neural network in JavaScript▲20

    2015 · mindjs.net

17. 17SG
    Simple Gaming AI▲11

    2017 · github.com

18. 18AP
    AI programming game▲11

    2015 · bomberbots.com

19. 19EN
    Evolutionary Neural Net Checker AI▲5

    2012 · github.com

20. 20BT
    Beating the Optimal Stopping Rule with Game Specific Knowledge▲18

    2019 · ctsrc.github.io

21. 21IT
    I trained a chess engine to play like humans▲14

    I built 1e4.ai - a chess web app where you play against neural networks trained to mimic human Lichess players at specific Elo ranges. There's a separate model for each 100-point rating bucket from ~800 to 2200+, and the bots not only choose human-like moves but also burn clock time, play worse under time pressure, and blunder in human-like ways. Live demo: https://1e4.ai Code: https://github.com/thomasj02/1e4_ai A few things that might be interesting: - Trained on almost a full year of Lichess blitz games, around 1B total games - Architecture is an a small…

    May 2026

22. 22WD
    Well-documented neural networks in JavaScript▲11

    2016 · github.com

23. 23FC
    Feeding Cards Against Humanity responses into a neural net▲7

    2019 · cards-against-the-machine.glitch.me

24. 24DS
    DeepMind's Neural Arithmetic Logic Units in PyTorch▲8

    2018 · github.com

Ranked by how close each launch is in meaning, then by votes. Refine with a description →