open-science

Name: open-science
Author: ai4s-research

Verified

Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.

567stars

63forks

TypeScript

Installation

# Add to your Claude Code skills
git clone https://github.com/ai4s-research/open-science

Getting Started

Guides for using ai agents skills like open-science.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 7/5/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-07-05T07:26:04.234Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is open-science?

open-science is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by ai4s-research. Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills. It has 567 GitHub stars.

Is open-science safe to use?

Yes. open-science passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install open-science?

Clone the repository with "git clone https://github.com/ai4s-research/open-science" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is open-science written in?

open-science is primarily written in TypeScript. It is open-source under ai4s-research on GitHub, so you can review or fork the full source.

Are there alternatives to open-science?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh open-science against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

boss-skill agentic.nvim

Open Science Desktop

Local-first, model-agnostic AI research workbench for macOS, Windows & Linux.

Formerly Open Science. An open-source desktop alternative to Claude Science and similar AI-for-science workbenches — built with Tauri, MCP, agent skills, and reproducible artifacts. It connects agents, notebooks, files, figures, reports, runs, and review into one auditable desktop workflow.

🎉 Recognition: Open Science Desktop ranks #1 by scored-task average on ResearchClawBench, an end-to-end benchmark for autonomous scientific research agents (Pass@1 leaderboard, July 9, 2026).

✨ What it does
🎬 See it in action
🧪 Current capabilities
🔌 Skills and connectors
📦 Install
🚀 Build from source
🔒 Safety and privacy
🗂️ Repository layout
📌 Status
🤝 Contributing
📖 Citation
⚖️ License

What it does

Runs the whole research loop — from a broad direction to a finished paper: exploration, literature survey, hypothesis, experiment code, analysis, figures, and write-up, in one continuous, auditable session.

Autonomous research agents — the bundled ai4s-agent chains specialist skills end to end (explore → survey → experiment → write), and each stage drops a real, inspectable artifact into your workspace, not just a chat reply.
Everything traces back — figures, tables, reports, notebooks, and run outputs link to the exact code, inputs, environment, model output, and conversation that produced them.
Local-first and yours — sessions, data, provenance, notebooks, and run records live in local folders on your machine. Nothing leaves by default.
Model-agnostic runtime — the UI talks through packages/sdk to a bundled, pinned OpenCode sidecar. Bring your own model; providers, skills, and MCP servers stay pluggable.
Reproducible by construction — local, SSH/Slurm, Modal, and notebook-batch runs are captured as reproducible run records, not loose terminal scrollback.
Extensible — agent skills, MCP servers and one-click science connectors, / commands, ! shell mode, and a model-agnostic SDK.

See it in action

One prompt -> a complete, traceable analysis. Simulate data, fit a model, save a publication-grade figure, and write a report where every number traces to the code.

End-to-end dose-response analysis: the agent runs code and produces a fitted figure and a report

Every artifact traces back to its code, inputs, and conversation.

Artifact inspector showing a figure's generating code, inputs, and provenance

Literature -> verifiable report. Search papers, draft a manuscript rendered as a PDF, and audit citations, unsourced numbers, and figure/code consistency.

Literature survey producing a rendered PDF manuscript with a traceability review

The agent driving a Jupyter notebook with a live matplotlib figure

An experiment sweep table alongside a live analysis notebook

The skills library listing bundled scientific skills

Current capabilities

The research loop, as skills. One meta-skill runs the full pipeline; each stage is a self-contained skill that produces a real, gradeable artifact — runnable on any model OpenCode supports:

Skill	Role	Primary output
`ai4s-agent`	Runs the four skills below, in order	The full research package
`research-explorer`	Turn a broad direction into concrete topics	`research_exploration.md`, `topic_matrix.md`, `literature_pre_survey.md`
`literature-survey`	Write a literature survey	6–20 pp PDF, 60+ real citations, LaTeX source, taxonomy figures
`experiment-suite`	Build an experiment package	Design doc, runnable code, `results.json` with provenance, figures, report
`paper-writer`	Write a research paper	8–14 pp PDF, 200+ citations, 4–8 figures, tables
`mindmap-render`	Render a mindmap	Image generated from a `topic_matrix.md`
`integrity-auditor`	Audit a paper's integrity	Image / numerical / logical findings, 4-level evidence grading, `audit_report.md`

These ship in the ai4s-skills pack alongside first-party review skills and the office/document skills below.

Platform

Area	Current state
Desktop shell	Tauri 2 + React + TypeScript + Vite, with macOS, Windows, and Linux desktop builds.
Runtime	Bundled OpenCode sidecar, auto-started by the app, isolated from the user's own OpenCode config/data.
Sessions	Multi-session chat/history, dated workspace folders, global history across workspaces, `/` commands, and `!` shell mode.
Files	Global and per-session file browsing, context menu actions, external open/reveal, copy path, and local preview server.
Notebooks	Real `.ipynb` files, Python and R notebook creation, local kernel execution, managed Jupyter environment via bundled `uv`, and an Open JupyterLab action.
Runs	Append-only run logs, global SQLite run index, search/facets/pagination, local/remote surfaces, output links, logs, and reproduce prompts.
Provenance	`.openscience/provenance.jsonl` tracks file versions and links produced artifacts back to the run or edit that created them.
Review	Traceability, statistics-integrity, domain-check, large-file, publication-figure, remote-compute, and Modal run skills are bundled as first-party skills.
Viewers	PDF, image, video, HTML, Markdown, code, CSV/TSV tables with charts, DOCX, XLSX, PPTX, molecules, 3D meshes, genome tracks, FITS, DOS/DOSCAR, EIGENVAL bands, qcode, anomaly maps, and phase files.
Models	OpenCode provider catalog, OAuth/API-key provider flows, custom OpenAI-compatible endpoints, and local/provider-specific options supported by OpenCode.
Interface languages	English, Simplified Chinese, Japanese, Spanish, German, French, and Korean. Portuguese (Brazil) and Arabic are registered but not selectable yet.

Skills and connectors

Bundled skills are fetched for builds and releases instead of being committed into git history:

ai4s-skills pack from ai4s-research/ai4s-skills.
Office/document skills from the Apache-2.0 anthropics/skills repository: docx, pdf, pptx, and xlsx.
First-party core skills in runtime/skills/core/: traceability-review, stats-integrity, domain-check, large-file, publication-figures, remote-compute, and modal-run.

One-click science MCP connectors currently include:

Literature search: arXiv, PubMed, Crossref, Semantic Scholar, bioRxiv/medRxiv.
Biomedical databases: PubMed, ClinicalTrials.gov, MyVariant/ClinVar.
Materials Project.
FRED economic data.
Space weather.
Open-Meteo weather and climate.
USGS water data.

You can also add any local or remote MCP server from Settings. See docs/CONNECT_YOUR_TOOLS.md.

For a neutral positioning note, see Open Science Desktop vs OpenScience.

Install

Download the latest installer from the Releases page.

macOS: .dmg / .app, Apple Silicon and Intel, macOS 13 Ventura or later.
Windows: NSIS .exe and .msi, Windows 10/11 x64.
Linux: .deb and .rpm on x86_64 Linux.

Builds are not code-signed or notarized yet.

macOS: if Gatekeeper says the app is damaged or from an unidentified developer, install it into Applications and run:

xattr -cr "/Applications/Open Science.app"

Windows: if SmartScreen appears, choose More info -> Run anyway.

Linux:

sudo apt install ./OpenScience_*.deb
# or
sudo rpm -i OpenScience_*.rpm

Build from source

Prerequisites:

Node.js >= 20
pnpm 9
Rust toolchain
macOS, Windows, or Linux system dependencies required by Tauri

git clone https://github.com/ai4s-research/open-science
cd