patrick-kidger/equinox

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

71
/ 100
Verified

Equinox helps machine learning engineers and scientists build and train neural networks and scientific models using JAX. It takes your model definitions and data, then outputs trained models ready for deployment. This is for users already comfortable with JAX who need a flexible tool for advanced model building.

2,814 stars. Used by 18 other packages. Actively maintained with 5 commits in the last 30 days. Available on PyPI.

Use this if you are a machine learning engineer or scientist working with JAX and need a flexible, PyTorch-like approach to defining and training custom neural networks or scientific models.

Not ideal if you are new to machine learning or JAX and need a high-level framework that abstracts away many of the underlying details.

deep-learning-research scientific-modeling neural-network-design jax-development model-training
Maintenance 13 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

2,814

Forks

180

Language

Python

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

5

Dependencies

4

Reverse dependents

18

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/patrick-kidger/equinox"

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