Update: 2025.04.09-13.10

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• CHGNet (🥈19 · ⭐ 290 · 📉) - Pretrained universal neural network potential for charge-informed atomistic modeling https://chgnet.lbl.gov. Custom ML-IAP MD pretrained electrostatics magnetism structure-relaxation
• Scikit-Matter (🥉15 · ⭐ 81 · 📉) - A collection of scikit-learn compatible utilities that implement methods born out of the materials science and.. BSD-3 scikit-learn

Update: 2025.04.09

📈 Trending Up

Projects that have a higher project-quality score compared to the last update. There might be a variety of reasons, such as increased downloads or code activity.

• KLIFF (🥈18 · ⭐ 35 · 📈) - KIM-based Learning-Integrated Fitting Framework for interatomic potentials. LGPL-2.1 probabilistic workflows
• ChemCrow (🥈16 · ⭐ 730 · 📈) - Open source package for the accurate solution of reasoning-intensive chemical tasks. MIT ai-agent
• TorchSim (🥈16 · ⭐ 170 · 🐣) - Torch-native, batchable, atomistic simulation. MIT HTC UIP ML-IAP structure-optimization
• hippynn (🥈13 · ⭐ 76 · 📈) - python library for atomistic machine learning. Custom workflows
• dftio (🥈8 · ⭐ 8 · 📈) - dftio is to assist machine learning communities to transcript DFT output into a format that is easy to read or used by.. LGPL-3.0 data-structures workflows

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• MODNet (🥇16 · ⭐ 91 · 📉) - MODNet: a framework for machine learning materials properties. MIT pretrained small-data transfer-learning

➕ Added Projects

Projects that were recently added to this best-of list.

• Garden (🥇20 · ⭐ 26 · ➕) - FAIR AI/ML Model Publishing Framework. MIT model-repository
• cuEquivariance (🥇19 · ⭐ 210 · 🐣) - cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used.. Apache-2 rep-learn
• Introduction to AI-driven Science on Supercomputers: A Student Training Series (🥈11 · ⭐ 220 · ➕) - Unlicensed general-ml rep-learn language-models
• OpenEquivariance (🥉10 · ⭐ 47 · ➕) - OpenEquivariance: a fast, open-source GPU JIT kernel generator for the Clebsch-Gordon Tensor Product. BSD-3 rep-learn

Update: 2025.04.08

📈 Trending Up

Projects that have a higher project-quality score compared to the last update. There might be a variety of reasons, such as increased downloads or code activity.

• MatML (🥉7 · ⭐ 3 · 📈) - Tools for managing the MatML ecosystem. BSD-3 MD UIP rep-learn pretrained

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• M3GNet (🥉18 · ⭐ 280 · 📉) - Materials graph network with 3-body interactions featuring a DFT surrogate crystal relaxer and a state-of-the-art.. BSD-3 ML-IAP pretrained
• HamGNN (🥈7 · ⭐ 91 · 📉) - An E(3) equivariant Graph Neural Network for predicting electronic Hamiltonian matrix. GPL-3.0 rep-learn magnetism C-lang

➕ Added Projects

Projects that were recently added to this best-of list.

• DeePTB (🥇15 · ⭐ 71 · ➕) - DeePTB: A deep learning package for tight-binding approach with ab initio accuracy. LGPL-3.0 ML-DFT
• DP-GEN2 (🥈14 · ⭐ 38 · ➕) - 2nd generation of the Deep Potential GENerator. LGPL-3.0 ML-IAP MD workflows
• DeepModeling Projects (🥈10 · ⭐ 6 · ➕) - DeepModeling projects. CC-BY-4.0
• DeepMD-GNN (🥉9 · ⭐ 39 · ➕) - DeePMD-kit plugin for various graph neural network models. LGPL-3.0 rep-learn MD UIP C++
• DeepModeling Tutorials (🥉7 · ⭐ 15 · ➕) - Tutorials for DeepModeling projects. Unlicensed
• dftio (🥉6 · ⭐ 8 · ➕) - dftio is to assist machine learning communities to transcript DFT output into a format that is easy to read or used by.. LGPL-3.0 data-structures workflows

Update: 2025.04.07-07.33

📈 Trending Up

Projects that have a higher project-quality score compared to the last update. There might be a variety of reasons, such as increased downloads or code activity.

• TorchSim (🥉14 · ⭐ 140 · 🐣) - Torch-native, batchable, atomistic simulation. MIT HTC UIP ML-IAP structure-optimization
• iam-notebooks (🥈10 · ⭐ 28 · 📈) - Jupyter notebooks for the lectures of the Introduction to Atomistic Modeling. Apache-2

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• Molfeat (🥈19 · ⭐ 200 · 📉) - molfeat - the hub for all your molecular featurizers. Apache-2 cheminformatics rep-eng rep-learn generative language-models pretrained
• MACE-FOUNDATION models (🥉18 · ⭐ 640 · 📉) - MACE-MP models. MIT ML-IAP pretrained rep-learn MD
• SLICES and MatterGPT (🥈14 · ⭐ 100 · 📉) - SLICES: An Invertible, Invariant, and String-based Crystal Representation [2023, Nature Communications] MatterGPT,.. LGPL-2.1 rep-eng language-models transformer materials-discovery structure-prediction
• Graph-Aware-Transformers (🥉5 · ⭐ 56 · 🐣) - Graph-Aware Attention for Adaptive Dynamics in Transformers. Apache-2 transformer graph-data pretrained single-paper

Update: 2025.04.07

📈 Trending Up

Projects that have a higher project-quality score compared to the last update. There might be a variety of reasons, such as increased downloads or code activity.

• pymatviz (🥇23 · ⭐ 200 · 📈) - A toolkit for visualizations in materials informatics. MIT general-tool probabilistic
• exmol (🥇22 · ⭐ 330 · 📈) - Explainer for black box models that predict molecule properties. MIT
• TorchSim (🥉13 · ⭐ 140 · 🐣) - Torch-native, batchable, atomistic simulation. MIT HTC UIP ML-IAP structure-optimization
• DeepErwin (🥉9 · ⭐ 54 · 📈) - DeepErwin is a python 3.8+ package that implements and optimizes JAX 2.x wave function models for numerical solutions.. Custom

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• FLARE (🥇18 · ⭐ 310 · 📉) - An open-source Python package for creating fast and accurate interatomic potentials. MIT C++ ML-IAP
• SpheriCart (🥇18 · ⭐ 83 · 📉) - Multi-language library for the calculation of spherical harmonics in Cartesian coordinates. MIT
• gptchem (🥈12 · ⭐ 250 · 💀) - Use GPT-3 to solve chemistry problems. MIT
• PiNN (🥈12 · ⭐ 110 · 📉) - A Python library for building atomic neural networks. BSD-3
• BenchML (🥉11 · ⭐ 15 · 💀) - ML benchmarking and pipeling framework. Apache-2 benchmarking

➕ Added Projects

Projects that were recently added to this best-of list.

• SMACT (🥇27 · ⭐ 110 · ➕) - Python package to aid materials design and informatics. MIT HTC structure-prediction electrostatics
• MACE-FOUNDATION models (🥉19 · ⭐ 640 · ➕) - MACE-MP models. MIT ML-IAP pretrained rep-learn MD
• AtomAI (🥈19 · ⭐ 210 · 💀) - Deep and Machine Learning for Microscopy. MIT computer-vision USL experimental-data
• ElementEmbeddings (🥈16 · ⭐ 41 · ➕) - Python package to interact with high-dimensional representations of the chemical elements. MIT XAI USL viz
• pySIPFENN (🥈16 · ⭐ 22 · ➕) - Python python toolset for Structure-Informed Property and Feature Engineering with Neural Networks. It offers unique.. LGPL-3.0 material-defect Disordered Materials pretrained transfer-learning
• ChemML (🥈15 · ⭐ 160 · ➕) - ChemML is a machine learning and informatics program suite for the chemical and materials sciences. BSD-3 cheminformatics active-learning workflows
• SLICES and MatterGPT (🥇15 · ⭐ 100 · ➕) - SLICES: An Invertible, Invariant, and String-based Crystal Representation [2023, Nature Communications] MatterGPT,.. LGPL-2.1 rep-eng language-models transformer materials-discovery structure-prediction
• xtal2png (🥈14 · ⭐ 37 · 💀) - Encode/decode a crystal structure to/from a grayscale PNG image for direct use with image-based machine learning.. MIT computer-vision
• Bgolearn (🥈13 · ⭐ 91 · ➕) - [Materials & Design 2024] A Bayesian global optimization package for material design Adaptive Learning | Active.. MIT materials-discovery probabilistic
• mat_discover (🥈13 · ⭐ 41 · 💤) - A materials discovery algorithm geared towards exploring high-performance candidates in new chemical spaces. MIT materials-discovery rep-eng HTC
• Awesome-Scientific-Language-Models (🥈11 · ⭐ 560 · ➕) - A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (EMNLP24). MIT language-models general-ml pretrained multimodal
• nablaDFT (🥈11 · ⭐ 200 · ➕) - nablaDFT: Large-Scale Conformational Energy and Hamiltonian Prediction benchmark and dataset. MIT ML-DFT ML-WFT drug-discovery ML-IAP benchmarking
• PDynA (🥉11 · ⭐ 41 · ➕) - Python package to analyse the structural dynamics of perovskites. MIT MD
• pumml (🥈11 · ⭐ 37 · 💀) - Positive and Unlabeled Materials Machine Learning (pumml) is a code that uses semi-supervised machine learning to.. MIT materials-discovery
• MPDS API (🥈11 · ⭐ 27 · ➕) - Tutorials, notebooks, issue tracker, and website on the MPDS API: the data retrieval interface for the Materials.. CC-BY-4.0 community-resource literature-data
• MLforMaterials (🥉7 · ⭐ 79 · ➕) - Online resource for a practical course in machine learning for materials research at Imperial College London.. MIT community-resource general-ml rep-eng <a href="ht...

Update: 2025.01.02

📈 Trending Up

Projects that have a higher project-quality score compared to the last update. There might be a variety of reasons, such as increased downloads or code activity.

• dgl-lifesci (🥇24 · ⭐ 740 · 💀) - Python package for graph neural networks in chemistry and biology. Apache-2
• ChemCrow (🥇18 · ⭐ 660 · 📈) - Open source package for the accurate solution of reasoning-intensive chemical tasks. MIT ai-agent
• GT4SD (🥇18 · ⭐ 340 · 📈) - GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process. MIT pretrained drug-discovery rep-learn
• Orb Models (🥈18 · ⭐ 220 · 🐣) - ORB forcefield models from Orbital Materials. Custom ML-IAP pretrained
• Rascaline (🥇16 · ⭐ 49 · 📈) - Computing representations for atomistic machine learning. BSD-3 Rust C++

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• FAIR Chemistry datasets (🥇25 · ⭐ 940 · 📉) - Datasets OC20, OC22, etc. Formerly known as Open Catalyst Project. MIT catalysis
• MPContribs (🥇22 · ⭐ 37 · 📉) - Platform for materials scientists to contribute and disseminate their materials data through Materials Project. MIT
• DeepQMC (🥇20 · ⭐ 360 · 📉) - Deep learning quantum Monte Carlo for electrons in real space. MIT
• tinker-hp (🥉9 · ⭐ 82 · 📉) - Tinker-HP: High-Performance Massively Parallel Evolution of Tinker on CPUs & GPUs. Custom
• fplib (🥉8 · ⭐ 7 · 📉) - libfp is a library for calculating crystalline fingerprints and measuring similarities of materials. MIT C-lang single-paper

➕ Added Projects

Projects that were recently added to this best-of list.

• MLIPX - Machine-Learned Interatomic Potential eXploration (🥈14 · ⭐ 62 · 🐣) - Machine-Learned Interatomic Potential eXploration (mlipx) is designed at BASF for evaluating machine-learned.. MIT benchmarking viz workflows

Update: 2024.08.19-13.22

Removed category biomolecules in accordance with issue #125.

Update: 2024.08.15

📈 Trending Up

Projects that have a higher project-quality score compared to the last update. There might be a variety of reasons, such as increased downloads or code activity.

• paper-qa (🥇27 · ⭐ 3.8K · 📈) - LLM Chain for answering questions from documents with citations. Apache-2 ai-agent
• DScribe (🥇23 · ⭐ 390 · 📈) - DScribe is a python package for creating machine learning descriptors for atomistic systems. Apache-2
• pymatviz (🥇21 · ⭐ 150 · 📈) - A toolkit for visualizations in materials informatics. MIT general-tool probabilistic
• e3nn-jax (🥈20 · ⭐ 170 · 📈) - jax library for E3 Equivariant Neural Networks. Apache-2

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• dpdata (🥇23 · ⭐ 200 · 📉) - Manipulating multiple atomic simulation data formats, including DeePMD-kit, VASP, LAMMPS, ABACUS, etc. LGPL-3.0
• Best-of Machine Learning with Python (🥇21 · ⭐ 16K · 📉) - A ranked list of awesome machine learning Python libraries. Updated weekly. CC-BY-4.0 general-ml Python
• Open Databases Integration for Materials Design (OPTIMADE) (🥈17 · ⭐ 76 · 📉) - Specification of a common REST API for access to materials databases. CC-BY-4.0
• openmm-torch (🥈16 · ⭐ 180 · 📉) - OpenMM plugin to define forces with neural networks. Custom ML-IAP C++
• MatBench Discovery (🥈16 · ⭐ 82 · 📉) - An evaluation framework for machine learning models simulating high-throughput materials discovery. MIT datasets benchmarking model-repository

➕ Added Projects

Projects that were recently added to this best-of list.

• QH9 (🥈12 · ⭐ 470 · ➕) - A Quantum Hamiltonian Prediction Benchmark. CC-BY-NC-SA 4.0 ML-DFT
• DPA-2 (🥇26 · ⭐ 1.4K · ➕) - Towards a universal large atomic model for molecular and material simulation https://doi.org/10.48550/arXiv.2312.15492. LGPL-3.0 ML-IAP pretrained workflows datasets
• Graphormer (🥈16 · ⭐ 2K · ➕) - Graphormer is a general-purpose deep learning backbone for molecular modeling. MIT transformer pretrained
• OpenML (🥈16 · ⭐ 660 · 💤) - Open Machine Learning. BSD-3 datasets
• PMTransformer (🥇16 · ⭐ 82 · ➕) - Universal Transfer Learning in Porous Materials, including MOFs. MIT transfer-learning pretrained transformer
• SevenNet (🥉14 · ⭐ 86 · ➕) - SevenNet (Scalable EquiVariance Enabled Neural Network) is a graph neural network interatomic potential package that.. GPL-3.0 ML-IAP MD pretrained
• HydraGNN (🥈14 · ⭐ 56 · ➕) - Distributed PyTorch implementation of multi-headed graph convolutional neural networks. BSD-3
• ChatMOF (🥈13 · ⭐ 53 · ➕) - Predict and Inverse design for metal-organic framework with large-language models (llms). MIT generative
• MACE-MP (🥉12 · ⭐ 33 · ➕) - Pretrained foundation models for materials chemistry. MIT ML-IAP pretrained rep-learn MD
• Neural-Network-Models-for-Chemistry (🥈11 · ⭐ 59 · ➕) - A collection of Nerual Network Models for chemistry. Unlicensed rep-learn
• load-atoms (🥈11 · ⭐ 37 · ➕) - download and manipulate atomistic datasets. MIT data-structures
• AI4Chemistry course (🥈10 · ⭐ 130 · ➕) - EPFL AI for chemistry course, Spring 2023. https://schwallergroup.github.io/ai4chem_course. MIT chemistry
• HamGNN (🥈9 · ⭐ 49 · ➕) - An E(3) equivariant Graph Neural Network for predicting electronic Hamiltonian matrix. GPL-3.0 rep-learn magnetism C-lang
• AI for Science paper collection (🥉9 · ⭐ 43 · 🐣) - List the AI for Science papers accepted by top conferences. Apache-2
• Q-stack (🥈9 · ⭐ 14 · ➕) - Stack of codes for dedicated pre- and post-processing tasks for Quantum Machine Learning (QML). MIT excited-states general-tool
• MADICES Awesome Interoperability (🥉9 · ⭐ 1 · ➕) - Linked data interoperability resources of the Machine-actionable data interoperability for the chemical sciences.. MIT datasets
• Awesome-Graph-Generation (🥉8 · ⭐ 260 · ➕) - A curated list of up-to-date graph generation papers and resources. Unlicensed rep-learn
• Awesome Neural SBI (🥉8 · ⭐ 80 · ➕) - Community-sourced list of papers and resources on neural simulation-based inference. MIT active-learning
• SiMGen (🥉8 · ⭐ 11 · ➕) - Zero Shot Molecular Generation via Similarity Kernels. MIT viz
• Awesome-Crystal-GNNs (🥉7 · ⭐ 54 · ➕) - This repository contains a collection of resources and papers on GNN Models on Crystal Solid State Materials. MIT
• AIS Square (🥉7 · ⭐ 10 · 💤) - A collaborative and open-source platform for sharing AI for Science datasets, models, and workflows. Home of the.. LGPL-3.0 community-resource model-repository
• rho_learn (🥉7 · ⭐ 3 · ➕) - A proof-of-concept framework for torch-based learning of the electron density and related scalar fields. MIT
• ChargE3Net (🥉6 · ⭐ 28 · ➕) - Higher-order equivariant neural networks for charge density prediction in materials. <a href="http://bit.ly/34MB...

Update: 2024.07.04

📈 Trending Up

Projects that have a higher project-quality score compared to the last update. There might be a variety of reasons, such as increased downloads or code activity.

• DeePMD-kit (🥇28 · ⭐ 1.4K · 📈) - A deep learning package for many-body potential energy representation and molecular dynamics. LGPL-3.0 C++
• SchNetPack (🥇26 · ⭐ 750 · 📈) - SchNetPack - Deep Neural Networks for Atomistic Systems. MIT
• QUIP (🥈25 · ⭐ 340 · 📈) - libAtoms/QUIP molecular dynamics framework: https://libatoms.github.io. GPL-2.0 MD ML-IAP rep-eng Fortran
• Ultra-Fast Force Fields (UF3) (🥈15 · ⭐ 55 · 📈) - UF3: a python library for generating ultra-fast interatomic potentials. Apache-2
• SchNetPack G-SchNet (🥈14 · ⭐ 42 · 📈) - G-SchNet extension for SchNetPack. MIT

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• GPUMD (🥇21 · ⭐ 410 · 📉) - GPUMD is a highly efficient general-purpose molecular dynamic (MD) package and enables machine-learned potentials.. GPL-3.0 MD C++ electrostatics
• DP-GEN (🥇21 · ⭐ 280 · 📉) - The deep potential generator to generate a deep-learning based model of interatomic potential energy and force field. LGPL-3.0 workflows
• DIG: Dive into Graphs (🥈20 · ⭐ 1.8K · 📉) - A library for graph deep learning research. GPL-3.0
• gpax (🥇17 · ⭐ 190 · 📉) - Gaussian Processes for Experimental Sciences. MIT probabilistic active-learning
• SPICE (🥈11 · ⭐ 130 · 📉) - A collection of QM data for training potential functions. MIT ML-IAP MD

➕ Added Projects

Projects that were recently added to this best-of list.

• LLaMP (🥈11 · ⭐ 36 · ➕) - A web app and Python API for multi-modal RAG framework to ground LLMs on high-fidelity materials informatics. An.. BSD-3 materials-discovery cheminformatics generative MD language-models Python
• IPSuite (🥈14 · ⭐ 14 · ➕) - IPSuite is a Python toolkit for FAIR development and deployment of MLPs. EPL-2.0 workflows HTC Python active-learning community-resource MD
• ZnDraw (🥉16 · ⭐ 23 · ➕) - A powerful tool for visualizing, modifying, and analysing atomistic systems. EPL-2.0 MD generative JavaScript
• FAIR Chemistry datasets (🥇21 · ⭐ 700 · ➕) - Datasets OC20, OC22, etc. Formerly known as Open Catalyst Project. MIT catalysis
• fairchem (🥈19 · ⭐ 700 · ➕) - FAIR Chemistrys library of machine learning methods for chemistry. Formerly known as Open Catalyst Project (ocp). Unlicensed pre-trained rep-learn catalysis

Update: 2024.05.23

📈 Trending Up

Projects that have a higher project-quality score compared to the last update. There might be a variety of reasons, such as increased downloads or code activity.

• NequIP (🥇24 · ⭐ 540 · 📈) - NequIP is a code for building E(3)-equivariant interatomic potentials. MIT
• Open Catalyst datasets (🥇20 · ⭐ 660 · 📈) - The datasets of the Open Catalyst project, OC20, OC22. CC-BY-4.0
• ocp (🥈19 · ⭐ 660 · 📈) - ocp is the Open Catalyst Projects library of state-of-the-art machine learning algorithms for catalysis. Unlicensed
• Pre-trained OCP models (🥈19 · ⭐ 660 · 📈) - Pre-trained models released as part of the Open Catalyst Project. Unlicensed pre-trained
• Chemiscope (🥉17 · ⭐ 110 · 📈) - An interactive structure/property explorer for materials and molecules. BSD-3 JavaScript

📉 Trending Down

Projects that have a lower project-quality score compared to the last update. There might be a variety of reasons such as decreased downloads or code activity.

• DeepChem (🥇36 · ⭐ 5.2K · 📉) - Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology. MIT
• SchNetPack (🥇26 · ⭐ 730 · 📉) - SchNetPack - Deep Neural Networks for Atomistic Systems. MIT
• TorchMD-NET (🥇21 · ⭐ 280 · 📉) - Neural network potentials. MIT MD rep-learn transformer pre-trained
• NVIDIA Deep Learning Examples for Tensor Cores (🥈20 · ⭐ 13K · 📉) - State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and.. Custom educational drug-discovery
• mp-pyrho (🥉17 · ⭐ 34 · 📉) - Tools for re-griding volumetric quantum chemistry data for machine-learning purposes. Custom ML-DFT

➕ Added Projects

Projects that were recently added to this best-of list.

• calorine (🥉8 · ⭐ 10 · 💀) - A Python package for constructing and sampling neuroevolution potential models. https://doi.org/10.21105/joss.06264. Custom
• PyNEP (🥉2 · ➕) - A python interface of the machine learning potential NEP used in GPUMD. MIT
• SOMD (🥉1 · ➕) - AGPL-3.0 ML-IAP active-learning
• apax (🥈18 · ⭐ 11 · ➕) - A flexible and performant framework for training machine learning potentials. MIT