metatensor/metatrain

Train, fine-tune, and manipulate machine learning models for atomistic systems

64
/ 100
Established

This tool helps scientists and researchers in materials science and chemistry to train and evaluate machine learning models for atomistic systems. You input atomic structure data and desired target properties (like energy), and it outputs a trained model that can be directly used in various molecular dynamics simulations. It's designed for computational chemists, physicists, and materials scientists who need to simulate molecular behavior efficiently.

Used by 1 other package. Available on PyPI.

Use this if you need to quickly train or fine-tune various atomistic machine learning potential architectures and integrate them into molecular dynamics simulations.

Not ideal if your primary goal is general machine learning model development outside of atomistic simulations or if you require extensive customization beyond supported architectures.

atomistic-simulation materials-science computational-chemistry molecular-dynamics quantum-chemistry
Maintenance 10 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

61

Forks

24

Language

Python

License

BSD-3-Clause

Last pushed

Mar 12, 2026

Commits (30d)

0

Dependencies

14

Reverse dependents

1

Get this data via API

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

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