Games played by Laya
Games are the most popular way to show what a fast decision model can do. Each frame becomes a state, the model answers a typed question, and the game acts on the answer. The best demos also show where Laya needs help from ordinary code.
294 projects
flyagent
JamesKevinJones
Combines a Drosophila circuit simulation with an asynchronous typed-decision layer that can use Laya
tic-tac-toe-with-laya
enfyna
A C tic-tac-toe game uses the Laya System 1 model as its opponent
reflexarc
lumenform
A Python desktop pet uses optional Laya decisions to nudge its behavior
tetromino
tomayac
A browser tetromino game uses the Decisions API with selectable Laya and open-jev backends
laya-demo
foxnukem
Runs a Tower Bloxx browser agent that uses Laya to decide when to drop blocks
laya-balatro
StevenLi-phoenix
Trains Laya to choose actions in Balatro using simulator self-play and real-game tests
Laya-Dilemma-Lab
SherwinDesouza
Simulates cooperation decisions among 100 agents using the Laya model
2048GameDecision
Devikrishna545
Compares Jev and Laya playing 2048 and fine-tunes Laya for improved accuracy
Layagame
BrajamohanDas-afk
Runs an autonomous Pac-Man game in which the local Laya model chooses strategic moves
laya-mlx
Thar-Paing123
A native MLX runtime for running Laya typed-decision models on Apple silicon
laya-tetris
ArkAung
Experiments fine-tune Laya to play Tetris using text-based board features
22-minds
Satya141
Runs a football simulation where each player uses Laya to choose actions during play
laya-demo
vighnesh-chavan
Demonstrates Laya typed decisions in Doom and a custom pygame shooting game
laya-nethack
Leeleit
Adds Laya risk judgments to a NetHack bot and studies learning from human games
laya-robot
NIRUN-Weerawit
Uses Laya typed decisions to control a simulated robot arm through a LIBERO harness
laya-fine-tuning
bnap00
Guides fine-tuning Laya on a 6 GB GPU with Pac-Man and Pigeonhole examples
laya-poker
luisfer-cli
Lets players compete against Texas Hold'em bots that make decisions with Laya
Laya_plays_Doom
vipulcodess
Controls ViZDoom episodes using structured decisions from the local Laya model
last-house-zombie-siege
airesearchjishengyin
Runs a browser-based tactical survival game where Laya selects squad actions
tetris-laya
phoenixdna
Uses Laya to play Tetris against a human or a second Laya-controlled opponent
robotics_jev
Kraga922
Fine-tunes a Laya-style model on Alfworld and Libero datasets for robotic decision-making
bevy_laya
ParkSnoopy
Connects Laya inference to Bevy through an asynchronous request and response adapter
benchmark-llm-iot-laya-jev
alinembs
Compares local Laya and hosted Jev decisions for controlling MQTT-connected lights and a fan
decision-model-arena
dante01yoon
Compares four decision models, including local Laya, across games and image-based decisions
Run one locally
Snake on a Mac from laya-mlx:
pip install 'laya-mlx[demo]'
hf download aac6fef/laya-multilingual-mlx
laya-snake
The README reports 75.40 moves/s over 2,400 moves on an M3 Max with --optimize --max-speed, with zero deaths and two visible safety interventions. laya-coreml has a Neural Engine version at 49.1 to 50.0 decisions/s.
Flappy Bird on an Intel CPU from flappy-laya-openvino-cpu, with one noul question per frame:
pip install -r requirements.txt
python flappy_bird.py
Its README reports a mean 28 ms per decision with the INT8 OpenVINO model.
More games
- laya-pong: browser Pong with a native Laya paddle at 18.7 ms p50 on Metal.
- laya-vs-jev: Laya (MLX) and Jev (API) play Chrome's T-Rex side by side.
- laya-vs-jev-arena: a snake race and a fighting game, Laya vs Jev or vs a human.
- open-jev-laya: Gomoku, Big Two and a 3D maze entirely in the browser.
- laya-playground: Flappy, a lane runner and Tetris, plus an editor.
- kevala: Tetris in the browser on WebAssembly and WebGPU.
- Laya4j: Snake and a Spring Boot Tetris in Java.
What the demos teach
- Describe the state in words. In laya-pong, the model matched the reference controller when the state was a sentence and never moved when it was three numbers. The Flappy Bird author saw the same effect: with a JSON dict the model answered about 0.9 on every frame.
- Make options phrases. "move the paddle up" beat "up" in laya-pong: 5/5 correct against 3/5.
- Keep a planner and a safety layer. The Snake and T-Rex demos use planner features and a safety layer that can override unsafe moves. Their scores measure the whole system, not the model alone, and the READMEs say so.
More ways to use Laya