Find open-source science resources

Hierarchical Generation of Molecular Graphs using Structural Motifs.

A Python program to compute quasi-harmonic thermochemical data from Gaussian frequency calculations.

Ensemble of automated QM workflows that can be run through jupyter notebooks, command lines and yaml files.

Comprehensive survey of foundation models for weather and climate data understanding

Biomedical AI agents

Physics-informed ML and SciML

200+ AI for Science papers with Chinese interpretations

LLM agents across scientific domains

Autonomous AI scientist research

PINN research collection

LLM for scientific research papers

Curated scientific LLM papers (260+ models)

Parallel Computing and Scientific Machine Learning: MIT 18.337J/6.338J course materials (1.9k+ stars)

Graph neural network library for PyTorch enabling molecular modeling, materials discovery, protein interaction networks, and scientific knowledge graph learning (23.7k+ stars)

Computational fluid dynamics in JAX, enabling differentiable Navier-Stokes simulations with automatic differentiation for ML-accelerated CFD research, supporting turbulence modeling, convection-diffusion, and complex boundary conditions on CPUs and GPUs (Google Research, 947+ stars)

GPU-accelerated differentiable physics simulation engine built on NVIDIA Warp, supporting rigid/soft body, cloth, and gradient-based optimization for scientific ML, initiated by Disney Research, DeepMind, and NVIDIA (Linux Foundation, Apache 2.0, 2025)

End-to-end molecular dynamics engine built on PyTorch, enabling differentiable simulations with neural network potentials and GPU acceleration for machine learning-accelerated molecular dynamics (MIT License, 707+ stars)

Deep learning package for many-body potential energy representation and molecular dynamics, achieving quantum-mechanical accuracy with classical MD efficiency (DeepModeling, Gordon Bell Prize 2020, 1.9k+ stars)

High-performance molecular simulation toolkit

Microsoft's AI-powered ab initio biomolecular dynamics simulation achieving quantum-mechanical accuracy for proteins with 10,000+ atoms, orders of magnitude faster than DFT using protein fragmentation and ML force fields (Nature 2024)

Probabilistic programming

Euclidean neural networks for arbitrary point transformations enabling E(3)-equivariant deep learning, foundational library for building geometry-aware neural networks in molecular dynamics, materials science, and physics

Molecular dynamics analysis

Machine learning in Julia

SDK & library for AI-driven scientific computing applications

Unified interface for local, global, gradient-based and derivative-free optimization (800+ stars)

Scientific machine learning benchmarks & differential equation solvers

Acausal modeling framework for automatically parallelized scientific machine learning (1.5k+ stars)

High-performance ML research

15TB collection of 16 large-scale numerical simulation datasets spanning fluid dynamics, MHD, astrophysics, biological systems, and acoustic scattering, with unified PyTorch dataloaders and benchmarks for training foundation models on physical sciences (Polymathic AI, NeurIPS 2024)

Large-scale benchmark suite for protein fitness prediction and design, aggregating 200+ deep mutational scanning assays and clinical variant datasets across diverse protein families and taxa, with standardized zero-shot and supervised leaderboards for variant effect prediction, mutation effect prediction, and protein language model evaluation (OATML & Marks Lab, NeurIPS 2023 Spotlight, Datasets & Benchmarks)

Therapeutics Data Commons: 66 AI-ready datasets across 22 drug discovery tasks with 29 leaderboards, covering target identification, molecular generation, ADMET prediction, and clinical trial outcomes (Harvard MIMS, NeurIPS 2021/2024)

Biomedical text generation

IBM's open foundation model family for materials and chemistry, covering SMILES, SELFIES, molecular graphs, 3D atom positions, and electron density grids, with a unified toolkit for representation learning and downstream prediction/generation (Apache 2.0, 2024-2025)

NVIDIA's open-source platform for building and adapting biological AI models at scale, bundling ESM-2, Geneformer, MolMIM and DNA embedding models with recipes for single-GPU to multi-node training (2025)

Mathematical reasoning

Open language model for mathematics (7B/34B) trained on Proof-Pile-2, outperforming Minerva at equal scale on MATH benchmark, with tool use and formal theorem proving in Lean without finetuning (EleutherAI, ICLR 2024)

Open-source scientific multimodal foundation model built on a 235B MoE LLM and 6B vision encoder, continually pretrained on 5T tokens including 2.5T scientific-domain tokens, with strong results across chemistry, materials, life science, and earth science benchmarks (2025)

Large language model for science

Curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines, enabling reproducible social science research with AI agents (Stanford REAP & CoPaper.AI, 1.1K+ stars, 2026)

Modern LLM-native agent simulation platform for social science research and experimental design, providing a flexible framework for creating and managing intelligent agents in simulated environments (Tsinghua FIB Lab, 984+ stars, 2025)

Microsoft AI for Good Lab's open-source biodiversity research hub providing AI models, edge devices, and tools for wildlife monitoring and conservation, including MegaDetector (camera trap animal detection), SPARROW (species recognition), PytorchWildlife (conservation AI toolkit), and bioacoustics analysis pipelines (1K+ stars)

Vision foundation model for the tree of life, pretrained on diverse biological imagery across taxa for zero-shot species identification, trait extraction, and biodiversity research (Ohio State University Imageomics Institute)

Ecological modeling and conservation AI

Biological simulation tools

Multi-modal geospatial ML platform for agriculture and sustainability, fusing satellite imagery (RGB, SAR, multispectral), drone imagery, weather data, and sensor data for crop identification, carbon footprint estimation, and microclimate prediction (Microsoft Research, MIT License)

Agricultural machine learning platform

First any-to-any generative foundation model for Earth Observation, enabling unified multimodal understanding and generation across diverse satellite sensors and geospatial tasks through a single architecture (258+ stars)

University of Cambridge's foundation model for time-series satellite imagery, enabling efficient extraction of temporal patterns from Earth observation for land classification, canopy height prediction, and other remote sensing tasks

Semantic-enhanced multi-modal remote sensing foundation model for Earth observation (Nature Machine Intelligence 2025), enabling universal interpretation across diverse satellite imagery modalities with open-source weights and benchmarks