extropic-ai/thrml

Thermodynamic Hypergraphical Model Library in JAX

68
/ 100
Established

This is a specialized library for researchers and hardware engineers working with probabilistic graphical models, especially those exploring energy-based models. It helps simulate and prototype how these models would behave on new, energy-efficient computing hardware. You provide a definition of your probabilistic model, and it generates samples reflecting the model's underlying probabilities.

1,026 stars. Actively maintained with 1 commit in the last 30 days. Available on PyPI.

Use this if you are a researcher or hardware engineer developing or experimenting with novel hardware for probabilistic graphical models, particularly those that benefit from efficient block Gibbs sampling.

Not ideal if you are looking for a general-purpose machine learning library for tasks like image classification or natural language processing.

probabilistic-modeling energy-based-models hardware-prototyping statistical-physics computational-design
Maintenance 13 / 25
Adoption 10 / 25
Maturity 24 / 25
Community 21 / 25

How are scores calculated?

Stars

1,026

Forks

129

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

1

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/extropic-ai/thrml"

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