Open-source alternatives to PiNN

apax^1^2 is a high-performance, extendable package for training of and inference with atomistic neural networks. It implements the Gaussian Moment Neural Network model ^3^4. It is based on JAX and uses JaxMD as a molecular dynamics engine.

autoplex is still under very active development and larger modifications to the source code should be expected.

📘Documentation | 🛠️Installation | 📜Recipes | 🚀Quickstart

PyNEP is a python interface of the machine learning potential NEP used in GPUMD.

n2p2 - A neural network potential package

deepmd-gnn is a DeePMD-kit plugin for various graph neural network (GNN) models, which connects DeePMD-kit and atomistic GNN packages by enabling GNN models in DeePMD-kit.

A deep learning package for many-body potential energy representation and molecular dynamics

machine learning interatomic potentials aiida plugin

ocp is the Open Catalyst Project's library of state-of-the-art machine learning algorithms for catalysis.

This code automates the construction of datasets for machine learned interatomic potentials (MLIPs) through active learning. By automating job execution utilizing the Parsl framework, the active learning process can run for many iterations without human intervention. ALF breaks the process down…

The Neural Force Field (NFF) code is an API based on SchNet 1-4, DimeNet 5, PaiNN 6-7 and DANN 8. It provides an interface to train and evaluate neural networks for force fields. It can also be used as a property predictor that uses both 3D geometries and 2D graph information 9.

This package is part of QUIP (but with a different license!). In order to use it, you should clone QUIP with the --recursive option. QUIP is released under a GPL license , whereas GAP uses ASL (Academic Software License).

Workflow is a Python toolkit for building interatomic potential creation and atomistic simulation workflows.

A python library for calculating materials properties from the PES

TurboGAP (c) 2018-2023 by Miguel A. Caro and others (see "contributors" below for detailed authorship info).

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

This package implements the Allegro E(3)-equivariant machine learning interatomic potential.

NequIP is an open-source code for building E(3)-equivariant interatomic potentials.

Authors: K. Toepfer, L.I. Vazquez-Salazar

KLIFF is an interatomic potential fitting package that can be used to fit physics-motivated (PM) potentials, as well as machine learning potentials such as the neural network (NN) models.

The goal of this project is to promote the use of neural network potentials (NNPs) by providing highly optimized, open source implementations of bottleneck operations that appear in popular potentials. These are the core design principles.

1. Overview 2. Repo Contents 3. System Requirements 4. Installation Guide 5. Demos and Expected Results 6. License 7. Citation

.. inclusion-marker-preambule-start-first

For more details visit: sgdml.org Documentation can be found here: docs.sgdml.org

Tools for machine learnt interatomic potentials