JAXsaw: Visualizing Composable Neural Architectures in JAX
==========================================================

.. image:: /gallery/neuroscience/gallery.gif
   :alt: CNN, RNN, Autoencoder, GAN, and Transformer animations
   :width: 100%

JAXsaw is a lightweight, GPU-accelerated framework for building and exploring
neural networks in JAX. Its modular building blocks support architectures ranging
from dense networks and CNNs to transformers, autoencoders, and GANs.

The library supports model development, training, and evaluation, with documented
examples and visualizations for learning and experimentation.

.. toctree::
   :maxdepth: 2
   :titlesonly:

   docs/quickstart
   docs/guide
   docs/learning
   docs/api_tutorials
   docs/api_reference