mir-group/allegro
Allegro is an open-source code for building highly scalable and accurate equivariant deep learning interatomic potentials
This project helps materials scientists and computational chemists accelerate simulations by generating accurate predictions for how atoms interact. It takes atomic structure data and produces models that can predict energies and forces within molecular dynamics simulations much faster than traditional quantum mechanics calculations. Researchers in materials science, chemistry, and physics who perform atomistic simulations would use this.
467 stars.
Use this if you need to perform large-scale, long-duration atomistic simulations with high accuracy, often for materials discovery or molecular behavior studies.
Not ideal if you require quantum-mechanical accuracy for small systems where traditional ab initio methods are feasible or if you are not using the NequIP framework.
Stars
467
Forks
73
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mir-group/allegro"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
deepmodeling/deepmd-kit
A deep learning package for many-body potential energy representation and molecular dynamics
chemprop/chemprop
Message Passing Neural Networks for Molecule Property Prediction
Acellera/moleculekit
MoleculeKit: Your favorite molecule manipulation kit
mir-group/nequip
NequIP is a code for building E(3)-equivariant interatomic potentials
CederGroupHub/chgnet
Pretrained universal neural network potential for charge-informed atomistic modeling...