teddykoker/nequip-eqx

JAX implementation of the NequIP neural network interatomic potential

40
/ 100
Emerging

This tool helps computational chemists and materials scientists simulate molecular dynamics with high accuracy. It takes atomic structure data (like .xyz files) as input and provides highly accurate predictions for energies and forces between atoms, crucial for understanding material behavior. Researchers in academia or industry working on material science, drug discovery, or chemical engineering would use this.

Available on PyPI.

Use this if you need to perform atomistic simulations, such as molecular dynamics, and require a neural network-based interatomic potential that delivers competitive accuracy.

Not ideal if you primarily work with older GPU hardware that doesn't support TensorFloat-32, as performance benefits might be limited without configuration adjustments.

molecular-dynamics materials-science computational-chemistry atomic-simulations drug-discovery
Maintenance 10 / 25
Adoption 6 / 25
Maturity 24 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

MIT

Last pushed

Feb 24, 2026

Commits (30d)

0

Dependencies

9

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/teddykoker/nequip-eqx"

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