Update: 2023.06.12-20.27

➕ Added Projects

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

• Deep Graph Library (DGL) (🥇37 · ⭐ 12K · ➕) - Python package built to ease deep learning on graph,.. Apache-2
• DeepChem (🥇36 · ⭐ 4.4K · ➕) - Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry,.. MIT
• RDKit (🥇30 · ⭐ 2.1K · ➕) - BSD-3
• DeePMD-kit (🥇28 · ⭐ 1.1K · ➕) - A deep learning package for many-body potential.. ❗️LGPL-3.0
• Matminer (🥇27 · ⭐ 390 · ➕) - Data mining for materials science. ❗Unlicensed
• SchNetPack (🥇25 · ⭐ 600 · ➕) - SchNetPack - Deep Neural Networks for Atomistic Systems. ❗Unlicensed
• DScribe (🥇25 · ⭐ 320 · ➕) - DScribe is a python package for creating machine learning.. Apache-2
• QUIP (🥈25 · ⭐ 290 · ➕) - libAtoms/QUIP molecular dynamics framework:.. ❗Unlicensed
• paper-qa (🥇24 · ⭐ 2.6K · 🐣) - LLM Chain for answering questions from documents with citations. Apache-2
• e3nn (🥇23 · ⭐ 680 · ➕) - A modular framework for neural networks with Euclidean symmetry. ❗Unlicensed
• dgl-lifesci (🥇23 · ⭐ 580 · ➕) - Python package for graph neural networks in chemistry and.. Apache-2
• MEGNet (🥇22 · ⭐ 450 · ➕) - Graph Networks as a Universal Machine Learning Framework for.. BSD-3
• DP-GEN (🥇22 · ⭐ 220 · ➕) - The deep potential generator to generate a deep-learning.. ❗️LGPL-3.0
• dpdata (🥇22 · ⭐ 130 · ➕) - Manipulating multiple atomic simulation data formats, including.. ❗️LGPL-3.0
• kgcnn (🥈22 · ⭐ 75 · ➕) - Graph convolution with tf.keras. MIT
• NVIDIA Deep Learning Examples for Tensor Cores (🥇21 · ⭐ 11K · ➕) - State-of-the-Art Deep Learning scripts organized by.. ❗Unlicensed
• TorchANI (🥇21 · ⭐ 390 · ➕) - Accurate Neural Network Potential on PyTorch. MIT
• MAML (🥈21 · ⭐ 240 · ➕) - Python for Materials Machine Learning, Materials Descriptors, Machine.. BSD-3
• NequIP (🥇20 · ⭐ 390 · ➕) - NequIP is a code for building E(3)-equivariant interatomic potentials. MIT
• JARVIS-Tools (🥈20 · ⭐ 220 · ➕) - JARVIS-Tools: an open-source software package for.. ❗Unlicensed
• ocp (🥈19 · ⭐ 410 · ➕) - ocp is the Open Catalyst Projects library of state-of-the-art machine.. MIT
• exmol (🥇19 · ⭐ 240 · ➕) - Explainer for black box models that predict molecule properties. MIT
• FitSNAP (🥈19 · ⭐ 100 · ➕) - Software for generating SNAP machine-learning interatomic.. ❗️GPL-2.0
• FLARE (🥈18 · ⭐ 220 · ➕) - An open-source Python package for creating fast and accurate interatomic.. MIT
• e3nn-jax (🥈18 · ⭐ 110 · ➕) - jax library for E3 Equivariant Neural Networks. Apache-2
• MatGL (Materials Graph Library) (🥈18 · ⭐ 70 · ➕) - Graph deep learning library for materials. BSD-3
• Scikit-Matter (🥈18 · ⭐ 58 · ➕) - BSD-3 scikit-learn
• MALA (🥇18 · ⭐ 33 · ➕) - Materials Learning Algorithms. A framework for machine learning materials.. BSD-3
• M3GNet (🥈17 · ⭐ 160 · ➕) - Materials graph network with 3-body interactions featuring a DFT.. BSD-3
• XenonPy (🥈17 · ⭐ 110 · ➕) - XenonPy is a Python Software for Materials Informatics. BSD-3
• Chemiscope (🥇17 · ⭐ 86 · ➕) - BSD-3
• MAST-ML (🥈17 · ⭐ 82 · ➕) - MAterials Simulation Toolkit for Machine Learning (MAST-ML). MIT
• DADApy (🥇17 · ⭐ 63 · ➕) - Distance-based Analysis of DAta-manifolds in python. Apache-2
• Uni-Fold (🥇16 · ⭐ 260 · ➕) - An open-source platform for developing protein models beyond.. Apache-2
• QML (🥉16 · ⭐ 180 · 💀) - QML: Quantum Machine Learning. MIT
• ALIGNN (🥈16 · ⭐ 130 · ➕) - Atomistic Line Graph Neural Network. ❗Unlicensed
• sGDML (🥈16 · ⭐ 110 · ➕) - sGDML - Reference implementation of the Symmetric Gradient Domain.. MIT
• CatLearn (🥇16 · ⭐ 86 · ➕) - ❗️GPL-3.0
• benchmarking-gnns (🥈15 · ⭐ 2.2K · 💀) - Repository for benchmarking graph neural networks. MIT
• Uni-Mol (🥈15 · ⭐ 340 · ➕) - Official Repository for the Uni-Mol Series Methods. MIT
• MoLeR (🥇15 · ⭐ 180 · ➕) - Implementation of MoLeR: a generative model of molecular graphs which.. MIT
• Librascal (🥇15 · ⭐ 68 · ➕) - A scalable and versatile library to generate representations.. ❗️LGPL-2.1
• SpheriCart (🥇15 · ⭐ 34 · 🐣) - Multi-language library for the calculation of spherical.. Apache-2
• KLIFF (🥈15 · ⭐ 26 · ➕) - KIM-based Learning-Integrated Fitting Framework (KLIFF). ❗️LGPL-2.1
• CCS_fit (🥈15 · ⭐ 5 · ➕) - Curvature Constrained Splines. ❗️GPL-3.0
• n2p2 (🥈14 · ⭐ 180 · 💤) - n2p2 - A Neural Network Potential Package. ❗️GPL-3.0
• <a href="https://github.c...