aiqm/torchani

TorchANI 2.0 is an open-source library that supports training, development, and research of ANI-style neural network interatomic potentials. It was originally developed and is currently maintained by the Roitberg group.

71
/ 100
Verified

This tool helps computational chemists and materials scientists predict atomic forces and energies using neural network models. You input molecular structures or atomic configurations, and it provides highly accurate energy and force calculations for use in simulations. It is designed for researchers who work with molecular dynamics and quantum chemistry problems.

540 stars. Used by 1 other package. Available on PyPI.

Use this if you need to rapidly and accurately calculate interatomic potentials for molecular simulations or material property predictions.

Not ideal if you are looking for a general-purpose machine learning library or if you primarily work with classical force fields without neural network integration.

computational-chemistry molecular-dynamics materials-science quantum-chemistry atomic-scale-simulation
Maintenance 10 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

540

Forks

137

Language

Python

License

MIT

Last pushed

Mar 04, 2026

Commits (30d)

0

Dependencies

13

Reverse dependents

1

Get this data via API

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

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