apax-hub/apax
A flexible and performant framework for training machine learning potentials.
This project helps computational chemists and materials scientists train and use machine learning models to predict how atoms and molecules interact. You provide atomic structure data, and it generates a specialized machine learning potential that can then be used to simulate molecular dynamics, offering a faster way to explore material properties or chemical reactions. It is designed for researchers working on atomistic simulations.
Available on PyPI.
Use this if you need to quickly train and deploy high-performance machine learning models to simulate the behavior of atoms and molecules.
Not ideal if you are looking for a general-purpose machine learning framework outside of atomistic simulations or need to implement a custom potential that is not neural network-based.
Stars
36
Forks
7
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Dependencies
16
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/apax-hub/apax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/