atomisticnet/aenet

SevenNet - a graph neural network interatomic potential package supporting efficient multi-GPU parallel molecular dynamics simulations.

AIMNet2: Fast and accurate machine-learned interatomic potential for molecular dynamics simulations

MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.

An open-source Python package for creating fast and accurate interatomic potentials.

NequIP is a code for building E(3)-equivariant interatomic potentials

The deep potential generator to generate a deep-learning based model of interatomic potential energy and force field

GRACE models and gracemaker (as implemented in TensorPotential package)

Code for automated fitting of machine learned interatomic potentials.

Torch-native, batchable, atomistic simulations.