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.
JAX - A curated list of resources https://github.com/google/jax
| Date | Stars |
|---|---|
| 2026-07-24 | 2137 |
| 2026-07-25 | 2137 |
| 2026-07-28 | 2137 |
| 2026-07-30 | 2137 |
| 2026-08-06 | 2137 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<!--lint ignore double-link-->
# Awesome JAX [](https://awesome.re)[<img src="https://raw.githubusercontent.com/google/jax/master/images/jax_logo_250px.png" alt="JAX Logo" align="right" height="100">](https://github.com/google/jax)
<!--lint ignore double-link-->
[JAX](https://github.com/google/jax) brings automatic differentiation and the [XLA compiler](https://www.tensorflow.org/xla) together through a [NumPy](https://numpy.org/)-like API for high performance machine learning research on accelerators like GPUs and TPUs.
<!--lint enable double-link-->
This is a curated list of awesome JAX libraries, projects, and other resources. Contributions are welcome!
## Contents
- [Libraries](#libraries)
- [Models and Projects](#models-and-projects)
- [Videos](#videos)
- [Papers](#papers)https://github.com/jax-ml/jax
- [Tutorials and Blog Posts](#tutorials-and-blog-posts)
- [Books](#books)
- [Community](#community)
<a name="libraries" />
## Libraries
- Neural Network Libraries
- [Flax](https://github.com/google/flax) - Centered on flexibility and clarity. <img src="https://img.shields.io/github/stars/google/flax?style=social" align="center">
- [Flax NNX](https://github.com/google/flax/tree/main/flax/nnx) - An evolution on Flax by the same team <img src="https://img.shields.io/github/stars/google/flax?style=social" align="center">
- [Haiku](https://github.com/deepmind/dm-haiku) - Focused on simplicity, created by the authors of Sonnet at DeepMind. <img src="https://img.shields.io/github/stars/deepmind/dm-haiku?style=social" align="center">
- [Objax](https://github.com/google/objax) - Has an object oriented design similar to PyTorch. <img src="https://img.shields.io/github/stars/google/objax?style=social" align="center">
- [Elegy](https://poets-ai.github.io/elegy/) - A High Level API for Deep Learning in JAX. Supports Flax, Haiku, and Optax. <img src="https://img.shields.io/github/stars/poets-ai/elegy?style=social" align="center">
- [Trax](https://github.com/google/trax) - "Batteries included" deep learning library focused on providing solutions for common workloads. <img src="https://img.shields.io/github/stars/google/trax?style=social" align="center">
- [Jraph](https://github.com/deepmind/jraph) - Lightweight graph neural network library. <img src="https://img.shields.io/github/stars/deepmind/jraph?style=social" align="center">
- [Neural Tangents](https://github.com/google/neural-tangents) - High-level API for specifying neural networks of both finite and _infinite_ width. <img src="https://img.shields.io/github/stars/google/neural-tangents?style=social" align="center">
- [HuggingFace Transformers](https://github.com/huggingface/transformers) - Ecosystem of pretrained Transformers for a wide range of natural language tasks (Flax). <img src="https://img.shields.io/github/stars/huggingface/transformers?style=social" align="center">
- [Equinox](https://github.com/patrick-kidger/equinox) - Callable PyTrees and filtered JIT/grad transformations => neural networks in JAX. <img src="https://img.shields.io/github/stars/patrick-kidger/equinox?style=social" align="center">
- [Scenic](https://github.com/google-research/scenic) - A Jax Library for Computer Vision Research and Beyond. <img src="https://img.shields.io/github/stars/google-research/scenic?style=social" align="center">
- [Penzai](https://github.com/google-deepmind/penzai) - Prioritizes legibility, visualization, and easy editing of neural network models with composable tools and a simple mental model. <img src="https://img.shields.io/github/stars/google-deepmind/penzai?style=social" align="center">
- [Levanter](https://github.com/stanford-crfm/levanter) - Legible, Scalable, Reproducible Foundation Models with Named Tensors and JAX. <img src="https://img.shields.io/github/stars/stanford-crfm/levanter?style=social" align="center">
- [EasyLM](https://github.com/young-geng/EasyLM) - LLMs made eaExcerpt of 48,680 characters
Read on GitHub
171
16
5
Mehdi Ataei · @NVIDIA · Canada
4
8bitmp3
4
4
Kevin P Murphy · Google
3
Eric Ma · @modernatx · United States
3
Stjepan Jureković · Manning Publication · Croatia
3
3
3
3
3
2
Saurav Maheshkar · United Kingdom
2
2
2
Neil Girdhar
2
2
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1540b9491f234fff, topic:deep-learning, topic:neural-network, topic:jax
matched fp:1540b9491f234fff, topic:awesome, topic:awesome-list, desc:curated list