Liangting

LASP-D3. C

NEP-kappa. NEP + HiPhive/Finite-Displacement + Phono3py workflow for lattice thermal conductivity

MACE-ICTC. MACE-ICTC re-expresses MACE/e3nn angular algebra using an irreducible Cartesian tensor basis. Fixed Q/U operators preserve MACE interaction and readout semantics while enabling dense-kernel-friendly execution, native mace-torch checkpoint conversion, AOTInductor export, and LAMMPS deployment.

simpoly. Python

academic-research-skills-codex. Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

jse. Java Simulation Environment: A Java software for assisting atomic simulation

tdep. The Temperature Dependent Effective Potentials (TDEP) code

nvalchemi-toolkit. ALCHEMI Toolkit is a developer toolkit for accelerating training and inference for AI in chemistry and material science.

Multi-Layer-Moire-Generator-MLM. A python code to create moire structure for material simulations with two and more twisted layers.

PhonoMC. PhonoMC: A C++ phonon Monte Carlo simulator for nanoscale semiconductor heat transport.

nebwalk. Minimal, correct Nudged Elastic Band (NEB) implementation for ASE — works with EMT, Egret-1t, MACE-MP-0, or any ASE-compatible calculator.

doped. doped is a Python software for the generation, pre-/post-processing and analysis of defect supercell calculations, implementing the defect simulation workflow in an efficient, reproducible, user-friendly yet powerful and fully-customisable manner.

ReciNet. Reciprocal space-aware long-range modeling for crystalline property prediction (TMLR 2026)

THEMol. Python

nvalchemi-toolkit-ops. ALCHEMI Toolkit-Ops is a collection of optimized batch kernels to accelerate computational chemistry and material science workflows.

pfd-kit. Fine-tuning and distillation workflow for pretrained atomic potentials

PESMaker. Foundation-potential-assisted workflow for application-oriented machine-learning potential dataset generation.

Gaunt-Tensor-Product. [ICLR 2024 Spotlight] Official Implementation of "Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products"

awesome-ai4s. AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai

UniSim. This is the official repository for our paper "UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules" published in ICML 2025.

GeoFormer. [ACM MM 2024] GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer

moltemplate. A general cross-platform tool for preparing simulations of molecules and complex molecular assemblies

tace. Tensor Atomic Cluster Expansion

euclidean_fast_attention. Implementation of the Euclidean fast attention (EFA) algorithm

Awesome-ML-Electrolytes-Electrochemical-Interfaces.

mattersim. MatterSim: A deep learning atomistic model across elements, temperatures and pressures.

molvis. [WIP] interactive molecule visualization lib

dpeva. Deep Potential Evolution Accelerator

GPUMD-skill. Python

Hamster.jl. Hamster.jl is a powerful Julia package to fit and run calculations with effective Hamiltonians to compute temperature-dependent optoelectronic properties.

GPUMD. Graphics Processing Units Molecular Dynamics

torch-dftd. pytorch implementation of dftd2 & dftd3 (not actively maintained)

mlipx. 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.

mlipx. 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.

Manybody-Heat-Current-MTP-LAMMPS-interface. Deposit for Input data for " Revisit Many-body Interaction Heat Current and Thermal Conductivity Calculation in Moment Tensor Potential/LAMMPS Interface" (2024)

ElePhAny.jl. Electron-phonon coupling with any functional

matgl. Graph deep learning library for materials

mPFDNN. mPFDNN, the Material-Property-Field-based Deep Neural Network in Hopfield Framework

MLIP_HOT. a toolkit for universal Machine Learning Interatomic Potential (uMLIP) based calculations, including structure optimization, formation energy calculation, and distance above convex hull calculation.

fMLP_conductivity. Thermal Conductivity Predictions with Foundation Atomistic Models

Prediction-of-Exfoliation-in-Two-Dimensional-Materials. Prediction of Exfoliation in Two-Dimensional Materials

pwtools. pwtools is a Python package for pre- and postprocessing of atomistic calculations, mostly targeted to Quantum Espresso, CPMD, CP2K and LAMMPS. It is almost, but not quite, entirely unlike ASE, with some tools extending numpy/scipy. It has a set of powerful parsers and data types for storing calculation data.

out-of-plane-polarization. A python program used for out-of-plane polarization in two-dimensional ferroelectrics

electrostatic-calculator. A python calculator that can calculate the electrostatic long-range forces and stress tensor from Born effective charges and the dielectric tensor.

lammps-MatPL. The LAMMPS interface for the machine learning force field of MatPL.

SevenNet. SevenNet - a graph neural network interatomic potential package supporting efficient multi-GPU parallel molecular dynamics simulations.

Phonon-Thermal-and-Mechanical-Properties-via-MLPs. A computational toolkit embedded with machine learning potentials (MLPs) for predicting mechanical properties, phonon dispersions, lattice thermal conductivity, and quasi-harmonic approximation (QHA)-based thermodynamic properties.

MolCryst. Molecular Crystals Database for Machine Learning Interatomic Potential. Access to foundation models for specific crystal structures and their constructed dataset.

VASP-Python. This is the data file associated with the publication "User-defined Electrostatic Potentials in DFT Supercell Calculations: Implementation and Application to Electrified Interfaces"

SpinDFT. Using high-throughput DFT, Wannier90, and TB2J, this project calculates the magnetic exchange interactions of 2D CrI3 under mechanical strain to reveal how structural distortions modulate its Heisenberg parameters.

PySCES. AI-LSC-IVR is a code written in Python3 and used to perform ab initio nonadiabatic dynamics using linearized semiclassical initial value representation (LSC-IVR).

AtomMOF. Implementation for AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction

matbench. Matbench: Benchmarks for materials science property prediction

PySlice. PySlice is a Python package for simulating and analyzing multslice simulations from molecular dynamics trajectories. In addition to standard multislice simulations such as diffraction and HAADF image generation, it implements the TACAW method to convert time-domain electron scattering data into frequency-domain spectra.

Toonflow-app. Toonflow 是开源一站式 AI 短剧创作工具，将小说、剧本快速转化为动画短剧。集成 AI 编剧、智能分镜、角色与视频生成，跨平台桌面端轻量部署，助力创作者低成本批量产出视觉内容。Toonflow is an open-source AI tool that turns stories and scripts into animated short dramas. Features AI scriptwriting, storyboarding, character and video generation. A cross-platform desktop app for efficient content creation.

al-folio. A beautiful, simple, clean, and responsive Jekyll theme for academics

roboto_origin. Roboto_origin Fully Open-Source DIY Humanoid Robot/萝博头原型机全开源手搓级人形机器人

mace-ft-tutorial. Python

materials. Foundation Model for Materials - FM4M

PropMolFlow. SE(3) Equivariant Flow Matching for Property-Guided Molecule Generation.

SOG-Net. Sum-of-Gaussians Neural Network (SOG-Net) is a lightweight and versatile framework for integrating long-range interactions into machine learning force field.

torch-harmonics. Differentiable signal processing on the sphere for PyTorch

mlflow. The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

REICO. REICO-unbiased random sampling to generate diverse datasets encompassing a wide range of atomic configurations and bonding scenarios. EMLP trained by RECIO dataset can achieve genuine general and reactive performance across a variety of unseen systems.

mlfcs. 🔧 Python package for 3rd/4th-order force constant calculation via finite displacement method, with ML potential support & thermal disorder generation.

plumed2. Development version of plumed 2

chemsmart. CHEMSMART: Chemistry Simulation and Modeling Automation Toolkit

DPmoire. A tool for constructing accurate machine learning force fields in moir\'e systems

SchNet-vdW. ASE interface to perform dispersion-inclusive geometry optimizations with SchNet interatomic potentials

libmbd. Many-body dispersion library

GlassMLIP. Jupyter Notebook

tace-foundations. TACE foundational models

schnetpack. SchNetPack - Deep Neural Networks for Atomistic Systems

PhononBench. PhononBench is a phonon-based benchmark for large-scale dynamical stability evaluation of AI-generated crystals, featuring 100k+ structures, DFT-level MatterSim phonon calculations, and open-source high-throughput workflows.

water_ice_nep. Supplement files of paper "Thermodynamics of Water and Ice from a Fast and Scalable First-Principles Neuroevolution Potential"

mlcgmd. [TMLR 2023] Simulate time-integrated coarse-grained MD with multi-scale graph neural networks

spirit. Atomistic Spin Simulation Framework

tibercad. Multiscale device simulation tool

mlip-arena. 🌟 [NeurIPS '25 Spotlight] Fair and transparent benchmark of machine learning interatomic potentials (MLIPs), beyond basic error metrics https://openreview.net/forum?id=SAT0KPA5UO

E2Former. Python

uMLIP_thermal_conductivity. Python

DM2. Diffusion models for disordered materials

bamboo. BAMBOO (Bytedance AI Molecular BOOster) is an AI-driven machine learning force field designed for precise and efficient electrolyte simulations.

awesome-nano-banana. Awesome curated collection of images and prompts generated by gemini-2.5-flash-image (aka Nano Banana) state-of-the-art image generation and editing model. Explore AI generated visuals created with Gemini, showcasing Google’s advanced image generation capabilities.

2dynamics. A collection of machine-learning force field (MLFF) training sets for two-dimensional (2D) halide perovskites

Orchestr.AI. Machine Learning Force Fields Engines Suite

Swatches. Local Environment Classification in Graphs

mace-osaka24. MACE_Osaka24 models

mace. MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.

datasets_dft_accuracy. Data repository for the paper "How Accurate Are DFT Forces? Unexpectedly Large Uncertainties in Molecular Datasets"

mlip-cleavage-benchmark. Benchmark for Machine Learning Interatomic Potentials (MLIPs) on surface stability and cleavage energy predictions

PTO-test. The file related to paper "Are Foundational Atomistic Models Reliable for Finite-Temperature Molecular Dynamics?"

berry-flux-diag. DFT pre- and post-processing package for effective polarization calculations using Berry flux diagonalization

ChargeDIFF. The first diffusion model for inorganic materials that explicitly incorporates electronic structure information

chemiscope. An interactive structure/property explorer for materials and molecules

FETmod. A module that can build atomic-level FET models is part of the NEP-FET workflow.

lips-25. Dataset and Benchmark Suite for MLIPs in Li-P-S Electrolyte Systems

ML4MoS2NT_ElectronicStructures. Model and scripts for the project of ML4MoS2NT_ElectronicStructures with using fine-tuning CHGNet MLIP and training a ML Hamiltonian model for MoS2 nanotube systems

AIS-Square.

CeNEP.

hoomd-blue. Molecular dynamics and Monte Carlo soft matter simulation on GPUs.

datasets. 🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

MOFFlow. Implementation for MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks

trajcast. TrajCast: Force-Free MD Through Autoregressive Equivariant Networks

LiTraj. Datasets for benchmarking machine learning models for predicting Li-ion migration

plumed_tutorial_mace. Repository holding all the files required for PLUMED online tutorial.

flashTP. Torch-native C++/CUDA library to accelerate tensor-product layers in MLIPs

so3lr. SO3krates and Universal Pairwise Force Field for Molecular Simulation

AstrBot. AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

cuEquivariance. cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural networks. Also includes kernels for accelerated structure prediction.

mace-unfolded. A package to compute the heat flux for MACE machine-learned force fields

Paper_Projects. This GitHub repository contains additional information supporting published manuscripts

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

nanochat. The best ChatGPT that $100 can buy.

YPHON. YPHON is a package that calculates phonon properties using a mixed-space approach with force constants derived from VASP.

chipsff. Evaluation of universal machine learning force-fields https://doi.org/10.1021/acsmaterialslett.5c00093

metatensor. Self-describing sparse tensor data format for atomistic machine learning and beyond

dftbplus. DFTB+ general package for performing fast atomistic simulations

simplegnn_version2. simple GNN potential version 2

cace. Python

ewald-summation. Efficient and easy to use fortran implementation of the Ewald summation method

auto-kappa. Automation software for calculating anharmonic phonon properties

phelel. Python

parsevasp. A general parser for VASP

MD-Raman. A tool for computing Raman Spectra from Molecular Dynamics

AMLP. AMLP integrates dataset creation, input/output handling, and analysis for machine learning interatomic potentials. It supports Gaussian, VASP, and CP2K, with LLM agents for code selection and ASE-based AMLP-Analysis for molecular simulations and validation.

reax_tools. A high performace ReaxFF/AIMD trajectory analysis tool based on graph theory.

ferrodispcalc. Python codes for calculation of polarization displacement vector in ferroelectric materials

gamma_SRME. Benchmarking machine learning interatomic potentials with Grüneisen parameter.

k_SRME. Heat-conductivity benchmark test for foundational machine-learning potentials

utils. Different utilities used by our group

SSE. Assessment and Application of Universal Machine Learning Interatomic Potentials in Solid-State Electrolyte Research

Tutorial-on-atomic-simulations. Tutorials on atomic simulations related to my research

aiida-trains-pot. An AiiDA workflow that implements a fully automated active learning scheme to train a neural network interatomic potential

SurFF. Python

Brillouin.jl. Brillouin zones and paths for dispersion calculations in Julia.

flare. An open-source Python package for creating fast and accurate interatomic potentials.

polflow. Workflows to automate polaron modeling

NeuralForceField. Neural Network Force Field based on PyTorch

ARTEMIS. Fortran code for generating and predicting interfaces between two crystals.

CUHK-PhD-Thesis-Template. Latex template for CUHK PhD Thesis

torchmd-protein-thermodynamics. Tutorials and data necessary to reproduce the results of publication Machine Learning Coarse-Grained Potentials of Protein Thermodynamics

torchmd. End-To-End Molecular Dynamics (MD) Engine using PyTorch

abTEM. ab initio Transmission Electron Microscopy

franken. ML potentials via transfer learning

packmol. Packmol - Initial configurations for molecular dynamics simulations

PhonoMatic. A high-throughput framework for automated harmonic and anharmonic phonon calculations using DFT and machine learning interatomic potentials (MLIPs).

SED. Spectral Energy Density analysis of phonon modes in 2D materials

CP-MACE. Python

MatterTune. A unified platform for fine-tuning atomistic foundation models in chemistry and materials science

phonon_angular_momentum. Python

PaCMAP. PaCMAP: Large-scale Dimension Reduction Technique Preserving Both Global and Local Structure

mofsim-bench. MOFSimBench: Evaluating universal machine learning interatomic potentials in metal-organic framework molecular modeling

gpu4pyscf. A plugin to use Nvidia GPU in PySCF package

e3nn. A modular framework for neural networks with Euclidean symmetry

GPUMDkit. A Toolkit for GPUMD&NEP

leopold. Python

Neural-Network-Models-for-Chemistry. A collection of Neural Network Models for chemistry

tools. Some scripts for gpumd and nep

GPUMD-Tutorials. Tutorials related to GPUMD

DistMLIP. DistMLIP: A Distributed Inference Library for Fast, Large Scale Atomistic Simulation

CUHK-PHD-Thesis-Template. CUHK PhD Thesis Template

LAMBench. A benchmark for Large Atomistic Models

matbench-discovery. An evaluation framework for machine learning models simulating high-throughput materials discovery.

camp_run. Cartesian Atomic Moment Potentials -- CAMP

pyhtstack2d-master. Python

ffonons. Phonons from ML force fields

abEELS. EELS simulations from MD simulations

HT-Phonon-MLIP. Data and python scripts for journal publication on "Accelerating High-Throughput Phonon Calculations via Machine Learning Universal Potentials"

pySED. Spectral Energy Density - for Molecular Dynamics simulations

fairchem. FAIR Chemistry's library of machine learning methods for chemistry

DeePTB. DeePTB: A deep learning package for tight-binding Hamiltonian with ab initio accuracy.

lammps. Compiled binaries and sources of LAMMPS, redistributed by AdvanceSoft Corp.

Phonon_hydrodynamics. Phonon hydrodynamics window using Guyer's condition [Phys. Rev. 148, 778 – Published 12 August 1966].

excitonwebsite. Visualize excitonic wavefunctions

OVITO_python_modifier_db. Collection of python script modifiers for OVITO Pro (https://www.ovito.org)

debyer. Debye's scattering equation & other analysis of atomistic models.

nepx. A tools to process the outputdata from NEP, include the MD part from GPUMD. NEPX, x is everything.

atomistic-cookbook. A collection of simulation recipes for the atomic-scale modeling of materials and molecules

GPUMD-Wizard. Material structure processing software based on ASE (Atomic Simulation Environment)

APFEforPI. Automated physical feature engineering for polymer informatics (APFEforPI), which has been utilized for the exploitation of high thermal conductivity amorphous polymers

dftd4. Generally Applicable Atomic-Charge Dependent London Dispersion Correction

mace. MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.

HamGNN. An E(3) equivariant Graph Neural Network for predicting electronic Hamiltonian matrix

materials_discovery. Jupyter Notebook

MOF-hardness. Support Information for Size-dependent hardness of metal-organic framework crystals: The effect of local amorphization induced by indentation

Toy-MD. Python code for learning Molecular Dynamics simulations

EPW-nano. Modified EPW code for first principles calculation of electron transport and thermoelectric property of materials, including electron-phonon scattering, defect scattering, and phonon drag.

i-pi. i-PI: a universal force engine

nonEquilibriumGreensFunction. Calculates transport dynamics of a customizable channel and contact configuration in the Non-Equilibrium Green's Function Formalism

Electronic-structure-calculations-course. Matherials for the course Electronic structure calculations

2DM-GAP. Machine learning potentials for Two-Dimensional Materials

VASP_OPT_AXIS. Fix lattice component(s) during relaxation in VASP

paper-reading. 深度学习经典、新论文逐段精读

python-sscha. The python implementation of the Stochastic Self-Consistent Harmonic Approximation (SSCHA).

PyEPFD. Python library for computing electron-phonon renormalizations from finite displacements

Project_Langevin_thermostat. A molecular dynamics simulation code

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

jarvis. About JARVIS-Tools: an open-source software package for data-driven atomistic materials design. Publications: https://scholar.google.com/citations?user=3w6ej94AAAAJ https://www.youtube.com/@dr_k_choudhary

jarvis-tools-notebooks. This repository is no longer maintained. For the latest updates and continued development, please visit: https://github.com/atomgptlab/jarvis-tools-notebooks