cassiusfive/balatro-gym

Gymnasium Environment for Balatro

42
/ 100
Emerging

This project helps AI researchers and game developers create and test AI agents for the poker-themed roguelike deck-builder game, Balatro. It takes in game states as observations and allows AI models to output actions, providing a standardized way to train reinforcement learning algorithms specifically for Balatro gameplay.

No commits in the last 6 months.

Use this if you are developing or researching AI agents for the game Balatro and need a consistent environment to train and evaluate your models.

Not ideal if you are a Balatro player looking for gameplay tips, strategies, or an AI to play the game for you out-of-the-box, as this is a developer tool for creating such AIs.

AI-research game-AI-training reinforcement-learning game-development Balatro
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

36

Forks

11

Language

Python

License

MIT

Last pushed

Jul 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cassiusfive/balatro-gym"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.