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

🏆 A ranked list of awesome atomistic machine learning projects ⚛️🧬💎.

Allegro is an open-source code for building highly scalable and accurate equivariant deep learning interatomic potentials

[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

[ICLR 2023 Spotlight] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs

SO3krates and Universal Pairwise Force Field for Molecular Simulation

Machine-Learned Interatomic Potential eXploration (mlipx) is designed at BASF for evaluating machine-learned interatomic potentials (MLIPs). It offers a growing set of evaluation methods alongside powerful visualization and comparison tools.

python library for atomistic machine learning

A Python library and command line interface for automated free energy calculations

UF3: a python library for generating ultra-fast interatomic potentials

Fair and transparent benchmark of machine learning interatomic potentials (MLIPs), beyond basic error metrics https://openreview.net/forum?id=ysKfIavYQE

KIM-based Learning-Integrated Fitting Framework for interatomic potentials.

FLAME: a library for atomistic modeling environments

A flexible and performant framework for training machine learning potentials.

PotentialLearning.jl: Optimize your atomistic data and interatomic potential models in your molecular dynamics workflows.

Generator of polynomial machine learning potentials

JAX implementation of the NequIP neural network interatomic potential

Fitting interatomic potential for molecular dynamics

A user package of LAMMPS software enabling simulations using linearized machine learning potentials

Cartesian Atomic Moment Potentials -- CAMP