google-deepmind/dm-haiku

JAX-based neural network library

62
/ 100
Established

This is a library for machine learning researchers and engineers who build neural networks using JAX. It helps convert Python functions that define neural network architectures, including their learnable parameters, into pure functions compatible with JAX's transformations. You provide a description of your network, and Haiku gives you back functions to initialize and apply it, making it easier to manage model state and integrate with JAX's automatic differentiation and parallelization tools.

3,199 stars. Actively maintained with 7 commits in the last 30 days.

Use this if you are developing neural network models with JAX and prefer an object-oriented programming style for defining your network layers, similar to Sonnet for TensorFlow.

Not ideal if you are starting a new project with JAX, as Google DeepMind now recommends Flax, which offers more features, documentation, and a larger community.

deep-learning neural-network-development machine-learning-research model-building scientific-computing
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

3,199

Forks

282

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-deepmind/dm-haiku"

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