chgnet

GUI for running simulations with universal MLIPs (MACE, CHGNet, SevenNet, Nequix, ORB, Allegro, MatterSim, UPET, GRACE)

Run machine-learning potentials using VASP style inputs.

A Python package for amorphous structure generation by melt-quench simulation and random placement.

Staged workflow for nonlinear phonon screening and QE recheck.

GNoME-style active learning on a pretrained CHGNet potential — 95% top-100 recall at a 20% labeling budget

Discovery of new high entropy alloy using materials informatics and machine learning