Find open-source science resources

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

End-to-end autonomous AI research engine that turns an idea into a complete LaTeX paper by dispatching real computational experiments to local GPUs or SLURM clusters, collecting actual results, generating figures/tables, and writing a data-grounded manuscript rather than LLM hallucinations (OpenRaiser, 1.5K+ stars, MIT License, 2026)

SDK & library for AI-driven scientific computing applications

Generalized biological foundation model with unified nucleic acid and protein language, integrating DNA/RNA/protein sequences (Nature Machine Intelligence 2025)

Automated cell type annotation tool for single-cell transcriptomics using gradient boosting and logistic regression with reference atlases, enabling standardized classification across datasets (Wellcome Sanger Institute, Nature Biotechnology 2022)

Multimodal LLM-based AI agent enabling deep research in spatial transcriptomics, automating analysis and interpretation of spatial gene expression data (Harvard LiuLab, bioRxiv 2025)

LLM agents for working with the SRA (Sequence Read Archive) and associated bioinformatics databases, enabling natural language querying of high-throughput sequencing data and metadata across genomic repositories (Arc Institute, 169+ stars, 2024-2026)

Flow-based generative model for atomistic protein binder design with test-time optimization, SOTA on binder benchmarks (ICLR 2026 Oral, NVIDIA)

DeepMind's neural network for ab-initio quantum chemistry, directly solving the many-electron Schrödinger equation via variational Monte Carlo with antisymmetric wavefunctions, extended to excited states (Phys. Rev. Research 2020, Science 2024)

Biological vision foundation model trained on TreeOfLife-200M, yielding extraordinary accuracy on diverse biological visual tasks including habitat classification and trait prediction despite a narrow training objective (Ohio State University Imageomics Institute)

Google Research's hybrid ML/physics atmospheric model combining learned dynamics with physical constraints, outperforming traditional models on 2-15 day forecasts and 40-year climate simulation, developed with ECMWF (Nature 2024)

Large transformer-based single-cell foundation model pretrained on 50 million cells for robust gene network inference, expression denoising, cell embedding, and zero-shot label prediction, leveraging ESM2 protein embeddings and bidirectional transformer architecture (Cantini Lab, 148+ stars, GPL-3.0)

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)

Knowledge graph-guided synthetic data generation for LLM fine-tuning, achieving strong performance on scientific QA (GPQA-Diamond) and math reasoning (AIME)

All-atom biomolecular structure prediction for protein-nucleic acid-small molecule-metal ion complexes, enabling accurate modeling of covalent modifications and assemblies beyond proteins (Baker Lab, Science 2024)

Automatic atomic model building program for cryo-EM maps using deep learning, enabling rapid de novo protein structure determination from electron density with high accuracy (3DEM/EMBL, 169+ stars)

Parallel symbolic regression network evaluating millions of expressions on GPU with automated subtree reuse, Nature Computational Science cover article (MIT, 2026)

Deployable biomedical deep-research agent blueprint combining on-prem multimodal RAG, report generation, human-in-the-loop editing, and virtual screening with MolMIM and DiffDock for drug discovery workflows (2025)

First scientific ML benchmark with paired real-world measurements and matched numerical simulations for complex physical systems, featuring 5 scenarios, 700+ trajectories, 10 baseline models, and 9 evaluation metrics with HuggingFace datasets and model checkpoints (Westlake University, CC BY-NC 4.0)

First fully customizable open-source multiagent framework automating complete research lifecycle from idea conception to LaTeX papers with dynamic workflows

General multimodal protein design framework enabling DNA-encoding of chemistry for programmable enzyme design and diverse protein generation through diffusion-based generative modeling (190+ stars, Apache 2.0, 2026)

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)

Fast and accurate protein structure search using a learned 3Di structural alphabet (VQ-VAE) that discretizes tertiary interactions into structural tokens, enabling protein-universe-scale structural alignment at sequence-search speeds (4-5 orders of magnitude faster than DALI/TM-align) and underpinning many AI4S tools such as SaProt, ESMAtlas search, and AFDB clustering pipelines (Steinegger Lab, Nature Biotechnology 2023)

Multimodal AI bridging transcriptomics data and natural language, enabling intuitive chat-based exploration and analysis of single-cell RNA-seq datasets through conversational interaction without coding; fine-tuned Mistral 7B LLaVA model emulating biologist-bioinformatician discussions (207+ stars, GPL-3.0)

Deep learning with spiking neural networks in Python, providing gradient-based training of SNNs via PyTorch autodifferentiation for brain-inspired computing and neuromorphic research, with online learning capabilities and extensive tutorials (1.9K+ stars, actively maintained)

Learning operators in Fourier space

A toolbox for machine learning in seismology, providing unified interfaces for deep learning seismic phase picking, earthquake detection, and waveform analysis across multiple benchmark datasets and pretrained models (397+ stars, actively maintained)

Simple and accurate de novo protein binder design pipeline using AlphaFold2 backpropagation, MPNN, and PyRosetta for automated binder discovery (bioRxiv 2024)

Open-source self-supervised vision foundation model for Earth observation by Clay Foundation (non-profit), a Masked Autoencoder ViT pretrained on multimodal satellite imagery (Sentinel-1/2, Landsat 8-9, NAIP, MODIS, LINZ DEM) with location/time embeddings, supporting classification, segmentation, change detection, similarity search, and few-shot downstream geospatial tasks (Apache 2.0, v1.5 2024-2025)

Fast, all-atom SE(3)-equivariant diffusion model for protein design achieving state-of-the-art performance on unconditional generation, motif scaffolding, and binder design while retaining the computational efficiency of equivariant architectures (bioRxiv 2026)

PyTorch-based differentiable programming framework for physics-informed system identification, parametric constrained optimization, and model predictive control, integrating neural operators, neural ODEs, KANs, SINDy, and differentiable predictive control with 30+ tutorials (1.3k+ stars, BSD License)

Medical large vision-language model unifying comprehension and generation via heterogeneous knowledge adaptation, enabling holistic medical image understanding, visual question answering, and clinical report generation across diverse modalities (ZJU4HealthCare, 1.6K+ stars)

Curated collection of papers, datasets, benchmarks, code, and pre-trained weights for Remote Sensing Foundation Models (RSFMs), tracking the rapidly evolving landscape of vision, vision-language, generative, and agent-based geospatial AI (1.9K+ stars, 2024-2026)

Closed-loop multi-agent system from hypothesis to verification across 12 scientific tasks, #1 on MLE-Bench (36.44%)

Trainable PyTorch reproduction of AlphaFold 3

Autonomous AI scientist research

Benchmark quantifying end-to-end autonomous AI research abilities of LLM agents across 20 tasks from SOTA machine learning papers spanning NLP, code, math, biochemical modelling, and time series forecasting, with normalized score metrics against human SOTA and HuggingFace dataset

General-purpose RNA language model with 650M parameters pretrained on 36M non-coding RNA sequences, achieving strong generalization on structure prediction tasks including secondary structure prediction, splice-site prediction, mean ribosome loading, and ncRNA classification (lbcb-sci, 165+ stars, Apache-2.0)

First physics-aligned interactive benchmark for LLM agents in engineering construction, designing rockets/cars/bridges in physics simulator with 3D spatial geometry library

LLM-driven machine learning engineering agent using agentic tree search to autonomously draft, debug and benchmark ML code; wins 4× more medals than the best linear agent on OpenAI's MLE-Bench (75 Kaggle competitions) (1.3K+ stars, MIT License)

Semi-flexible molecular diffusion model for structure-based drug design with reinforcement learning, achieving 20× faster sampling and providing a no-code web platform for molecular design (ISPC Lab, Tongji University, 2026)

Classic open-source plugin for document Q&A and summarization within Zotero

Incremental knowledge graph construction using LLMs with entity extraction and Neo4j visualization

102 executable tasks from 44 peer-reviewed papers across 4 disciplines with containerized evaluation

Single-cell analysis with transformers

Arc Institute's single-cell foundation model enabling in-context learning at inference time via a novel tabular attention architecture, trained on 150M uniformly-preprocessed cells for generalizing biological effects and generating unseen cell profiles in novel contexts (2025)

Generative AI system for antibiotic discovery that searches billions of synthesizable molecules by combining molecular building blocks through real chemical reactions, experimentally validating novel compounds active against drug-resistant bacteria

Fast spike sorting with drift correction for extracellular electrophysiology, enabling universal neural spike sorting via deep learning on high-density neural probe recordings (MouseLand, 609+ stars)

RFdiffusion is an open source method for structure generation, with or without conditional information (a motif, target etc).

Benchmark evaluating AI agents on 75 curated Kaggle-style ML engineering competitions with reproducible Docker-based grading harness, human baselines, and end-to-end task lifecycle, used as a primary benchmark for autonomous ML research agents (e.g., InternAgent #1 at 36.44%)