Find open-source science resources

Inflexa is an open-source, agentic orchestration platform for computational biology and translational medicine. It is designed to assist researchers in analyzing multi-omics, cheminformatics, and imaging data by reading published literature, designing multi-step analysis plans, and executing experiments with full reproducibility.

Free, open-source desktop AI research assistant that runs locally and turns natural-language requests into real data analysis, literature search, figure generation, and manuscript review; ships with 149 scientific skills, 326 workflow templates, and 229 databases across genomics, proteomics, drug discovery, and materials science, plus a living lab notebook, 60+ scientific file previews, and LaTeX editing (K-Dense-AI, 908+ stars, MIT License, 2026)

Open-source construction ERP with AI-powered cost matching, BOQ generation, and PDF/CAD/BIM takeoff; 42 regional catalogues, 21 languages, 71 modules (DataDrivenConstruction, 717+ stars, AGPL-3.0, 2026)

PureJsImage is a free, open-source TypeScript library for decoding, inspecting, processing, and converting ordinary images and scientific rasters in Node.js and modern browsers. It provides explicit readers for microscopy, whole-slide pathology, medical imaging, electron microscopy, spectroscopy, hyperspectral, and multidimensional array formats. These include OME-TIFF, OME-Zarr, Aperio SVS, DICOM, NIfTI, MRC/CCP4, NRRD, DigitalMicrograph, EMD, ENVI, and FITS. Range-backed readers can request selected regions, tiles, volume planes, and metadata while preserving native numeric samples where supported. The default package has no runtime dependencies. Optional JPEG and PNG WebAssembly accelerators require explicit registration.

Open-source AI workbench for scientific research that automates the full research loop — literature review, hypothesis generation, code writing, experiment execution, database querying, and report writing — with 290+ skills, specialized research agents, and a browser-based workspace (1453+ stars, Apache 2.0, 2026)

Self-evolving AI research colleague built on OpenClaw with 285+ runtime-adaptive skills across 28+ disciplines, persistent cross-session research memory, and zero-hallucination citation protocols; agent autonomously writes new SKILL.md files based on research patterns without redeployment (828+ stars, MIT License, 2026)

Local-first, open-source AI workbench for scientists — an open alternative to Claude Science (by ai4s-research, maintainers of this list; TypeScript, MIT, 2026)

Multi-type data labeling and annotation tool

edfcore is a zero-dependency TypeScript library for reading EDF, EDF+, BDF, and BDF+ physiological recordings in browser and Node.js applications. It provides programmatic access to biosignal samples, channel metadata, per-channel sampling rates, physical units, annotations, and discontinuous recording timelines.

Research agent system deeply integrated with Zotero supporting Agent Mode, skills, multi-model backends (OpenAI-compatible, Claude Code, WebChat, Codex), and MinerU PDF parsing for literature Q&A, summarization, figure inspection, and source comparison (1.3K+ stars, 2026)

A large RDF store built from American governmental data. This semantic space has a mixture of direct terms and subspaces.

Open-source 3D architectural editor with an AI design assistant; build floor plans with walls, doors, windows, and furniture using natural language, with real-time WebGPU-powered previews (TangSY, 59+ stars, MIT License, 2026)

Open-source, local-first, model-agnostic AI research workbench for reproducible scientific discovery; runs Python/R notebooks, searches the web, calls scientific data connectors, and produces inspectable reports, tables, and figures in a self-hosted desktop workspace (1.5K+ stars, Apache 2.0, 2026)

Curated, accuracy-first collection of benchmarks for evaluating LLMs on scientific reasoning and discovery across mathematics, physics, chemistry, materials science, biology, and agentic science (subinium, 29+ stars, MIT License, 2026)

A transparent, unit-aware calculator for the mathematical relationship between peptide mass, target concentration and solution volume. It normalizes mg, micrograms, mL and microlitres, shows the formula and includes a reference syringe visualization. Research-use-only software: it does not select a solvent, validate a laboratory method, calculate a dose or provide administration guidance.

Satellite-powered agricultural and land analytics platform combining Sentinel-2 imagery, Google Earth Engine processing, real-time weather data, soil science databases, and AI-driven crop planning into a unified web dashboard (145+ stars, AGPL-3.0, 2026)

Auto-generates clean, customizable academic CVs from open research data (OpenAlex, ORCID, Crossref, DataCite, Open Editors Plus). A single canonical CV object drives every output format (HTML, PDF, DOCX, LaTeX, Markdown); citations render through CSL; and the account holder is matched by persistent identifier (ORCID / OpenAlex ID) rather than name string. Free for individuals, open-source, and FAIR by design.

Visualization intermediate language that lets AI agents create expressive, polished charts from simple, human-editable specs, compiling the same input to 30+ chart types across Vega-Lite, ECharts, and Chart.js with an MCP server for agent integration (1.9K+ stars, MIT License, 2026)

AI-driven desktop workbench for computational materials science with an interactive 3D structure editor, natural-language CatBot assistant, visual DAG workflow engine, remote-cluster access, and HPC job submission for VASP, ORCA, CP2K, Quantum ESPRESSO, GPAW, DFTB+, SIESTA, and LAMMPS (172+ stars, AGPL-3.0, 2026)

An interactive structure/property explorer for materials and molecules.

Offline-first scientific writing workspace powered by Claude, integrating LaTeX, Python, and 100+ scientific skills with local execution, Zotero integration, and privacy-focused design (2026)

Standalone browser-based Gene Ontology network viewer for exploring, filtering, searching, and exporting GO term and gene annotation neighborhoods from locally preprocessed GO OBO and GAF data.

A RDF vocabulary for OER content on the web.

First system progressively surpassing human SOTA on frontier AI tasks (183.7%, 1.9%, 7.9% improvements), month-long autonomous discovery with 20,000+ GPU hours

2D interactive visualization in Jupyter.

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

Family of open time-series foundation models (MOMENT-1 small/base/large, T5-style encoder-only architecture with time series patching) pretrained on the curated Time Series Pile corpus, enabling zero/few-shot forecasting, classification, anomaly detection, imputation, and representation learning across scientific and real-world temporal data, with open weights on HuggingFace and pip-installable `momentfm` package (Auton Lab, CMU & UPenn, MIT License, 850+ stars)

Web application for LLM-assisted manuscript review and annotation

Point and click, cross platform suite for analysing and visualizing next-generation sequencing datasets.

Browser-based viewer for Sanger sequencing chromatograms in AB1/ABIF and SCF format, and for the .srd raw files of the Nanofor-05 capillary sequencer, converted to ABIF as they open. Shows raw and analysed traces, base calls (called or edited), per-base quality and the full ABIF directory, and puts two reads side by side with their tag tables aligned. A read aligns against a pasted or loaded reference, which reports identity, mismatches, indels and the ends that did not align, and flips the strand when the read is on the other one. End trimming (modified Mott or sliding window) has draggable handles, motif search is IUPAC-aware and finds primers, and QC metrics copy out as CSV. Drag on a trace to select a base range, then copy it as FASTA, zoom to it or export just that region. Exports the read as FASTA, FASTQ, .qual or ABIF and the chromatogram as a high-resolution PNG. Open files are kept as local sessions. Runs entirely in the browser — files are never uploaded.

Browser-based tool to open almost any file that carries sequence — FASTA, FASTQ, GenBank, EMBL, Swiss-Prot, AB1/ABIF, SCF, Clustal, Stockholm, PHYLIP, NEXUS, MSF, PIR, MEGA, GFF3, SAM, BAM, GFA, PDB and ACE — see every sequence inside, pick the ones you want, and save them as FASTA. The format is detected from the file content, not from the extension, so unlabelled or misnamed files still open, and gzip-compressed files are unpacked in place. Records can be filtered by length, name, GC or sequence type, reverse-complemented, transcribed DNA↔RNA or translated to protein, deduplicated and reordered before saving. Runs entirely in the browser — files are never uploaded.

Browser-based viewer for GenBank and GenPept records — .gb, .gbk, .gbff, .gp and plain GenBank text. Renders an interactive linear and circular feature map, including circular plasmid maps, alongside the annotated source text and the nucleotide/protein sequence. Translates CDS features using the record's own genetic code and translation qualifiers, flags where the stored /translation disagrees with a plain translation, and adds optional computed layers: ORF prediction and restriction-site mapping. Drag a range in the sequence band to select it, then copy that stretch — either strand, as DNA or as protein, plain or FASTA. Filters features by type, handles multi-record files, and keeps open records as local sessions, so a closed tab can be picked up where it was left. Runs entirely in the browser — files are never uploaded.

edf2csv is a local command-line tool for converting EDF, EDF+, BDF, and BDF+ physiological recordings into CSV and JSON files. It exports signal values, channel information, annotations, and recording metadata while preserving original sampling rates, physical units, and discontinuities.

Browser-based viewer that maps sequencing reads onto one short reference — an amplicon, gene or plasmid. Reads open as Sanger AB1/ABIF, SCF, FASTA, FASTQ or a SAM somebody else already mapped (gzipped files are unpacked in place); the reference as FASTA, GenBank or a read. Both read orientations are tried automatically. The pileup reports per-position depth, where reads disagree with the target, and the consensus — phred-weighted for capillary reads, which keep their chromatogram under the letters. An optional protein lane translates target and consensus side by side. Reads are placed by minimap2 compiled to WebAssembly, or by the built-in aligner. One read or the whole alignment saves as FASTA. Runs entirely in the browser — files are never uploaded.

Meniscus turns a raw microplate-reader export into a defensible quantitative result. It reads eight instrument formats, provides plate layout editing, fits standard curves with six models including 4PL and 5PL, back-calculates sample concentrations, and issues a quality-control verdict against stated thresholds. Every reported number can be expanded into the substituted formula that produced it. Analysis runs entirely in the browser with no upload and no backend. Numerical routines are validated against independent SciPy and NumPy implementations, published openly.