instadeepai/mlip

High level API for using machine learning models in OpenMM simulations

Graph deep learning library for materials

Pretrained universal neural network potential for charge-informed atomistic modeling https://chgnet.lbl.gov

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

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

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

Torch-native, batchable, atomistic simulations.

Code for automated fitting of machine learned interatomic potentials.

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.