machine-learning-potential

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

Graphics Processing Units Molecular Dynamics

AI-enhanced computational chemistry

GPU Monte Carlo Simulation Code with a taste of RASPA

Interface for simulations and standalone Python script generation with universal machine-learning interatomic potentials (MACE, CHGNet, SevenNet, NequIP, ORB, Allegro, MatterSim, UPET, GRACE, UMA, ALIGNN-FF)

Genarris is a random molecular crystal structure generator.

Meta's UMA and Orbital Materials' Orb-v3/OrbMol interatomic potential models, running on Tenstorrent hardware.

Useful scripts in Computaional Material Science.

Accelerating Metadynamics-Based Free-Energy Calculations with Adaptive Machine Learning Potentials

Endstate corrections from MM to QML potential

A lightweight Snakemake-based workflow that implements the DP-GEN scheme.

Collection of tools/codes/data used in the article D4DD00265B

Machine learning interatomic potentials and their application to lithium batteries (seminar talk in Spanish).

Loads Crystallography Open Database structures, filters them for CHGNet, and streams live relaxations after substitution, vacancy or strain edits. 27.8% of COD qualifies.

A minimal package for providing pretrained machine learning force fields (e.g. multi-fidelity M3GNet) for material simulations.

Companion code for Catal. Lett. 156(9) 2026: DFT → DeepMD → uncertainty-guided Bayesian optimization for SCR catalyst screening (9,726 DFT configurations, energy R² = 0.995, force R² = 0.963)

AIMNet2 hands-on tutorial: nine notebooks from a single-point energy to chemical reactivity. AiMat Summer School 2026, Machine Learning for Molecules

Evaluate the ensemble model deviation in the same fashion as DeepMD, integrate with ai2kit workflow for MACE

Physics bachelor's thesis project focused on testing the physical adequacy and physical foundations of MLIPs in the context of molecular simulations.

Reproducible CHGNet relaxation-energy pilot on Materials Project LLZO structures