Find open-source science resources

Research ecosystem for rigorous and trustworthy AI scientists — a protocol and skill bundle that makes autonomous research verifiable, crystallized, and observable through structured, machine-executable research artifacts and five agent skills for research management, compilation, verification, visualization, and publication (ARA-Labs, 447+ stars, MIT License, 2026)

spoQC is a modular framework for multimodal quality control (QC) of imaging-based spatially resolved transcriptomics (SRT). It independently evaluates cell segmentation, imaging, and transcript data to identify high-quality regions (HQRs) across entire tissue sections. In addition, spoQC uses Markov random fields (MRFs) to incorporate spatial dependencies and generate spatially refined QC masks.

Composite-objective protein design framework integrating Boltz, AlphaFold2, OpenFold3, ProteinMPNN, and ESM via JAX-based gradient optimization over continuous relaxed sequence space for multi-property binder design (319+ stars, MIT License, 2025)

Interactive and hardware-agnostic SDK for laboratory automation, enabling programmatic control of liquid handlers, plate readers, and other lab instruments across multiple vendors; foundational infrastructure for self-driving laboratories and AI-driven experimental execution (447+ stars)

PathForge is a modular benchmarking framework for multiple instance learning in computational pathology. It supports whole slide image feature extraction, HDF5 artifact generation, tile overviews, benchmarking, pipeline optimization, classification, regression, survival and retrieval tasks, and support for model inference and visualization.

AI coding agent skills for KiCad electronics design that turn Claude Code, Codex, Gemini CLI, and other coding agents into full electronics design assistants; parses schematics and PCB layouts, builds power trees, audits connectors/ESD protection, validates passive networks, runs SPICE simulation, sources components from major distributors, and prepares boards for fabrication (aklofas, 974+ stars, MIT License, 2026)

Hand-curated Snakemake pipelines to combine identifier cross-references from multiple sources across dozens of biomedical types, including anatomical entities, diseases and phenotypes, genes and proteins and many others.

Co-create PowerPoint presentations with Generative AI from documents or topics

Ensemble of automated machine learning protocols that can be run sequentially through a single command line. The program works for regression and classification problems.

PyTorch framework for training neural network interatomic potentials with the Equivariant Transformer (ET) architecture and its efficient TensorNet successor, providing equivariant message passing with linear complexity in tensor order; underpins the MACE-OFF and SPICE models and widely adopted across molecular dynamics and materials simulation workflows (Amsterdam Machine Learning Lab / De Fabritiis Group, 483+ stars, MIT License, actively maintained)

Continuously updated functional re-annotation of the Mycobacterium tuberculosis complex gene set, anchored on the MTBC0 ancestral genome rather than on a single strain. Serves one record per gene combining Pfam domains, ESMFold structures with Foldseek search, protein language-model features, orthology, curated knowledge, protein association networks and intra-species selection inferred from 145209 sequenced genomes, with dated sources and a graded confidence level for every field. Intended as a successor to Mycobrowser, which is no longer maintained.

A benchmark for ML-guided high-throughput materials discovery.

BRANCHSNV reports strict clade-exclusive nucleotide markers separately from single-nucleotide substitutions reconstructed on a selected edge of a rooted phylogenetic tree, while retaining ambiguity across equally parsimonious ancestral-state reconstructions.

E(3)-equivariant neural network interatomic potentials achieving DFT accuracy with up to 1000× less training data than invariant models, foundational architecture behind MACE and Allegro (Harvard, MIT, Nature Communications 2022)

MCP server, CLI, and agent skills for searching and downloading academic papers from multiple open sources (arXiv, PubMed, bioRxiv, Semantic Scholar, OpenAlex, CORE, Europe PMC, etc.) with unified, deduplicated, LLM-friendly retrieval and an OA-first download fallback chain (OpenAGS, 1.9K+ stars, MIT License, 2025)

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

Lightweight Markdown-only skills for autonomous ML research with cross-model review loops, idea discovery, and experiment automation; no framework lock-in, works with Claude Code, Codex, OpenClaw, or any LLM agent (12.8K+ stars, MIT License, 2026)

Beyond text-to-slides generation with PPTEval multi-dimensional evaluation (EMNLP 2025)

Shared multimodal AI agent layer for geospatial Python packages (leafmap, geoai, geemap, STAC, NASA Earthdata) and QGIS, exposing geospatial tools to LLMs with structured metadata, confirmation hooks, and support for OpenAI, Anthropic, Google Gemini, Ollama, and more; includes the OpenGeoAgent QGIS plugin (456+ stars, MIT License)

Unified pre-trained model for general physics simulation via lifted geometric pre-training, augmenting static geometry with synthetic dynamics to enable dynamics-aware self-supervision without physics labels; improves industrial-fidelity benchmarks spanning fluid mechanics and solid mechanics while reducing labeled data requirements by 20–60% (Physics-Scaling, 224+ stars)

Agent-agnostic research infrastructure providing AI agents with a structured scientific workspace for deep PDF parsing, hybrid semantic/keyword literature search, citation-graph analysis, topic discovery, and academic writing workflows; natively integrates with Claude Code, Codex, Cursor, Cline, and AgentSkills.io (530+ stars, MIT License, 2026)

Create MSP files containing the isotopic patterns for given molecules with given adducts. The tool is based on enviPat and the RforMassSpectrometry toolbox.

First agentic LLM for autonomous data science with end-to-end pipeline from data to analyst-grade reports

A toolkit for visualizations in materials informatics.

Open-source LLM-powered R&D agent framework automating data-driven AI solution building through automated research, development, and evolution; achieves top open-source performance on MLE-Bench with dual Researcher-Developer agents and supports research copilot, data mining, Kaggle, and quant R&D workflows (13.6K+ stars, MIT License, 2025-2026)

Scalable genomic analysis.

Unified Python framework for extracellular electrophysiology, standardizing interfaces to 10+ ML-based spike sorting algorithms including Kilosort for reproducible neural spike sorting workflows (792+ stars, actively maintained)

StaphScope is an automated, locally-executable computational pipeline designed specifically for comprehensive Staphylococcus aureus genomic surveillance. It addresses the critical bottleneck in MRSA research by integrating seven essential genotyping methods into a single, cohesive workflow.

Python package for segmenting geospatial data with the Segment Anything Model (SAM), enabling zero-shot object segmentation in satellite and aerial imagery for remote sensing and Earth observation (MIT, 4k+ stars)

PyTorch domain library for geospatial deep learning providing standardized datasets, samplers, transforms, and pre-trained models for remote sensing, land cover mapping, and environmental monitoring (Microsoft, 4K+ stars)

PseudoScope is an automated, locally-executable computational pipeline designed specifically for comprehensive Pseudomonas aeruginosa genomic surveillance. It integrates seven essential analysis modules into a single, cohesive workflow: FASTA QC (assembly quality metrics), MLST (Oxford scheme), PAST serotyping (O-antigen typing), AMRFinderPlus (antimicrobial resistance gene detection), ABRicate (multi-database screening for resistance, virulence, plasmids, biocides), Ultimate Reporter (gene-centric integration with interactive HTML), and Visualisation Dashboard (publication-ready interactive plots including PCA, networks, boxplots). PseudoScope runs entirely locally (or on HPC clusters), protects data privacy, and produces beautiful interactive reports in minutes.

Kleboscope is an automated, locally‑executable computational pipeline designed specifically for comprehensive Klebsiella pneumoniae genomic surveillance. It addresses the growing threat of multidrug‑resistant and hypervirulent K. pneumoniae by integrating eight essential analysis modules into a single, cohesive workflow. Kleboscope offers two complementary report views: Gene‑centric – each gene is shown with all genomes that contain it, together with its frequency, enabling rapid cross‑genome pattern discovery; and Sample‑centric – each isolate gets its own interactive box with typing badges (MLST, K‑locus, O‑locus, hypervirulence), per‑database tables (AMR, Virulence, BACMET, Plasmids), and full mutation details – perfect for clinical reports and patient‑level investigations.

Python library to train, interpret, and apply deep learning models to DNA sequences, providing a unified framework for regulatory genomics with support for CNN and transformer architectures, variant effect prediction, and attribution analysis (325+ stars)

AcinetoScope is an automated, comprehensive bioinformatics pipeline designed specifically for the genomic analysis of Acinetobacter baumannii, a WHO Critical Priority pathogen responsible for devastating hospital-acquired infections. It integrates seven analysis types (MLST, ABRicate, AMRFinder, Kaptive 3, APT, PlasmidFinder, and mutation detection) into a single automated workflow — from FASTA to actionable insights. The pipeline offers both gene-centric and sample-centric reporting, dynamic grouping by typing, and is optimised for HPC, cloud, and container environments.

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

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs (460+ stars, 2024)

Multi-agent system automatically transforming research papers into interactive AI agents with MCP server generation, tutorial auto-detection, and benchmark extraction (2.2K+ stars, MIT License, 2025)

Microsoft's generative model for sampling protein equilibrium conformations 100,000× faster than MD simulations, predicting domain motions, local unfolding and cryptic binding pockets on a single GPU (Science 2025)

Curated library of 550+ medical research agent skills spanning evidence insights, protocol design, omics/clinical data analysis, and academic writing; each skill is reviewed through MedSkillAudit and compatible with Claude Code, Codex, Open Code, OpenClaw, and SKILL.md-compatible agents (AIPOCH, 1.2K+ stars, MIT License, 2026)

Offline tool for cleaning tables of human gene and protein identifiers (TXT, CSV, TSV, XLSX). It maps approved symbols, aliases, previous symbols, Ensembl gene, UniProt, Entrez, RefSeq and HGNC identifiers to current HGNC approved symbols with cross-references, using a bundled HGNC snapshot. Excel date-corrupted symbols are recovered where the original is unambiguous and flagged for manual review otherwise; no input row is dropped. Each run records the tool version and HGNC release and writes a per-row audit table.

Minimalist, batteries-included repository for training video world models with diffusion-forcing, supporting long-horizon rollouts, 3D point-cloud generation, and model-predictive control with pretrained checkpoints (Simchowitz Lab, 700+ stars, MIT License, 2026)

Generates pre-miRNA and mature miRNA count tables from read alignments to pre-miRNA sequences and a gff file, both downloaded from mirBase. Produces also read coverage plots of pre-miRNAs.

PyTorch-native atomistic simulation engine for the machine-learned interatomic potential (MLIP) era, enabling batched molecular dynamics and structural relaxation with automatic GPU memory management; supports MACE, Fairchem, SevenNet, ORB, MatterSim and other popular MLIPs with up to 100x speedup over ASE (Radical AI, AI for Science 2026, 468+ stars, MIT License)

Open source PEM (Proton Exchange Membrane) fuel cell simulation tool.

HIDE-Deconv is a framework for characterizing cellular remodeling from bulk RNA-seq data using hierarchical cell-type deconvolution across multiple levels of cellular resolution. It provides an integrated workflow for single-cell reference preprocessing, estimation of cellular compositions, and downstream analysis of deconvolution results, including visualization, clustering, differential composition, and survival analysis.

Flow-matching protein folding model using only general-purpose transformer layers, scaled to 3B parameters and trained on 8.6M+ distilled structures; challenges the reliance on complex domain-specific architectures and supports PyTorch and MLX backends with model sizes from 100M to 3B parameters (985+ stars, MIT License)

Large-scale knowledge graph and pip-installable client for literature-grounded automated scientific research, connecting papers, authors, institutions, venues, keywords, citations, and a four-level research taxonomy across medicine, social sciences, engineering, computer science, materials science, and more (ZJU NLP, arXiv 2026, 136+ stars, MIT License)

RBPBench is a multi-function tool to evaluate CLIP-seq and other related genomic region data using a comprehensive collection of known RNA-binding protein (RBP) binding motifs. RBPBench can be used for a variety of purposes, from RBP motif search (database or user-supplied RBP motifs) in genomic regions, over motif enrichment and co-occurrence analysis, in-depth comparisons over multiple datasets via sequence and genomic annotation statistics, to benchmarking CLIP-seq peak caller methods as well as comparisons across cell types and CLIP-seq protocols. RBPBench supports both sequence and structure motifs, as well as regular expressions (sequence and structure patterns). Moreover, users can easily provide their own motif collections.

Microsoft's AI-powered geospatial Earth science application for natural-language exploration, visualization, and analysis of 130+ satellite collections, with STAC integration, multi-agent backend, MCP server, and deployable React/FastAPI stack (MIT, 2025)

The "FRamewOrk for Molecular AGgregate Excitations" enables localised QM/QM' excited state calculations in a solid state environment.