lanl/hippynn

python library for atomistic machine learning

56
/ 100
Established

This tool helps researchers in materials science and chemistry to build and train machine learning models for atomistic simulations. You input atomic structure data, and it outputs predictions for material properties like energy, forces, and charge. It is ideal for computational chemists, physicists, and materials scientists working with molecular dynamics or quantum chemistry simulations.

Use this if you need to efficiently train machine learning models to predict properties of atomic systems, especially for large datasets or complex architectures.

Not ideal if you are looking for a pre-built, ready-to-use model for a specific material without needing to train custom architectures.

atomistic-simulation materials-science computational-chemistry molecular-dynamics quantum-mechanics
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

94

Forks

34

Language

Python

License

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lanl/hippynn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.