
flax
by google (organization)
Flax is a neural network library for JAX that is designed for flexibility. (description from the project’s GitHub page)
Repository facts
- Stars
- 7,349
- Forks
- 849
- Open issues and pull requests
- 534
- Primary language
- Jupyter Notebook
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- google · Organization
- Created
- Jan 10, 2020
- Last push
- Oct 12, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 1,718: sanchit-gandhi/whisper-jax
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
4,678 starsJupyter NotebookApache-2.0Last push Apr 3, 2024
Rank 2,419: google/brax
Massively parallel rigidbody physics simulation on accelerator hardware.
3,249 starsJupyter NotebookApache-2.0Last push Oct 7, 2026
Rank 7,049: parrt/tensor-sensor
The goal of this library is to generate more helpful exception messages for matrix algebra expressions for numpy, pytorch, jax, tensorflow, keras, fastai.
806 starsJupyter NotebookMITLast push Apr 7, 2022
Rank 7,345: ikostrikov/jaxrl
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
757 starsJupyter NotebookMITLast push Oct 26, 2022
Rank 194: jax-ml/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
36,463 starsPythonApache-2.0Last push Oct 18, 2026