Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Flax is a neural network library for JAX that is designed for flexibility.
| Date | Stars |
|---|---|
| 2026-07-31 | 7281 |
| 2026-08-02 | 7285 |
| 2026-08-03 | 7286 |
| 2026-08-04 | 7286 |
| 2026-08-05 | 7289 |
| 2026-08-06 | 7292 |
Today
+3 stars today
This week
— stars this week
This month
— stars this month
Momentum
47.0
growth rate 0.00%/day
<div align="center"> <img src="https://raw.githubusercontent.com/google/flax/main/images/flax_logo_250px.png" alt="logo"></img> </div> # Flax: A neural network library and ecosystem for JAX designed for flexibility [](https://github.com/google/flax/actions/workflows/flax_test.yml) [](https://pypi.org/project/flax/) [**Overview**](#overview) | [**Quick install**](#quick-install) | [**What does Flax look like?**](#what-does-flax-look-like) | [**Documentation**](https://flax.readthedocs.io/) Released in 2024, Flax NNX is a new simplified Flax API that is designed to make it easier to create, inspect, debug, and analyze neural networks in [JAX](https://jax.readthedocs.io/). It achieves this by adding first class support for Python reference semantics. This allows users to express their models using regular Python objects, enabling reference sharing and mutability. Flax NNX evolved from the [Flax Linen API](https://flax-linen.readthedocs.io/), which was released in 2020 by engineers and researchers at Google Brain in close collaboration with the JAX team. You can learn more about Flax NNX on the [dedicated Flax documentation site](https://flax.readthedocs.io/). Make sure you check out: * [Flax NNX basics](https://flax.readthedocs.io/en/latest/nnx_basics.html) * [MNIST tutorial](https://flax.readthedocs.io/en/latest/mnist_tutorial.html) * [Why Flax NNX](https://flax.readthedocs.io/en/latest/why.html) * [Evolution from Flax Linen to Flax NNX](https://flax.readthedocs.io/en/latest/guides/linen_to_nnx.html) **Note:** Flax Linen's [documentation has its own site](https://flax-linen.readthedocs.io/). The Flax team's mission is to serve the growing JAX neural network research ecosystem - both within Alphabet and with the broader community, and to explore the use-cases where JAX shines. We use GitHub for almost all of our coordination and planning, as well as where we discuss upcoming design changes. We welcome feedback on any of our discussion, issue and pull request threads. You can make feature requests, let us know what you are working on, report issues, ask questions in our [Flax GitHub discussion forum](https://github.com/google/flax/discussions). We expect to improve Flax, but we don't anticipate significant breaking changes to the core API. We use [Changelog](https://github.com/google/flax/tree/main/CHANGELOG.md) entries and deprecation warnings when possible. In case you want to reach us directly, we're at [email protected]. ## Overview Flax is a high-performance neural network library and ecosystem for JAX that is **designed for flexibility**: Try new forms of training by forking an example and by modifying the training loop, not adding features to a framework. Flax is being developed in close collaboration with the JAX team and comes with everything you need to start your research, including: * **Neural network API** (`flax.nnx`): Including [`Linear`](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/linear.html#flax.nnx.Linear), [`Conv`](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/linear.html#flax.nnx.Conv), [`BatchNorm`](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/normalization.html#flax.nnx.BatchNorm), [`LayerNorm`](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/normalization.html#flax.nnx.LayerNorm), [`GroupNorm`](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/normalization.html#flax.nnx.GroupNorm), [Attention](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/attention.html) ([`MultiHeadAttention`](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/attention.html#flax.nnx.MultiHeadAttention)), [`LSTMCell`](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/recurrent.html#flax.nnx.nn.recurrent.LSTMCell), [`GRUCell`](https://flax.readthedocs.io/e
Excerpt of 7,905 characters
Read on GitHub
Cristian Garcia · Google · United Kingdom
472
409
393
Andreas Steiner · Google · Switzerland
285
Anselm Levskaya · United States
254
230
Marcus Chiam · Google DeepMind · United Kingdom
218
197
8bitmp3
103
Sam Anklesaria · Mongolia
87
vfdev · @openteams-ai
80
Mohit Reddy · xAI · United States
72
Daniel Suo · Google DeepMind · United States
60
60
Adam Roberts · @google · United States
39
35
joao guilherme
30
Alexey Gritsenko · Netherlands
28
27
Mohsin Mehmood · Kodamai · Pakistan
25
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:fa65cf41a362e4a6, topic:jax