ai-agent

openscience: Accelerate Your Research with a Powerful AI Workbench

Leverage a TypeScript‑based AI co‑scientist to streamline experiments, data analysis, and model building—ideal for founders building science‑focused products. 3.9k+ GitHub stars.
3,964 stars+62★ this week526 forksTypeScriptGuide quality 8/10 · reviewed Oct 9Updated 10/10/2026100% free · open source
What it does

OpenScience provides an AI-powered workbench for scientific research, enabling founders to streamline their research workflows and collaborate with others.

When to use it
  • •When conducting research that requires significant data analysis and processing
  • •When needing to collaborate with other researchers and track changes to research projects
  • •When looking for an open-source solution for research workflow management
Ready-to-paste prompt
Use the command `npm run start` to start the OpenScience workbench and access the dashboard for creating and managing research projects
Heads up: Before running the workbench, ensure you have Node.js (version 14 or higher) and npm installed on your system, as OpenScience relies on these dependencies to function properly
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/openscience && curl -fsSL https://workflowstacks.com/api/skills/openscience/claude-skill -o ~/.claude/skills/openscience/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How openscience: Accelerate Your Research with a Powerful AI Workbench works
Codeflow
Free to inspect

Openscience: Accelerate Your Research with a Powerful AI Workbench is a very large TypeScript project (~456k lines across 1719 code files, plus 626 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~456k lines · 1719 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
No API keys detected
TypeScript 70%Python 20%TeX 3%CSS 3%MDX 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    package.json
    Dependencies and the commands it exposes
What's in each folder
backend/Backend / API3435 files
frontend/Frontend / UI2243 files
docs/Documentation21 files
tooling/Folder134 files
evals/Evaluations & benchmarks35 files
.github/CI / automation (GitHub Actions)24 files
.openscience/Tool / agent settings11 files
.husky/Tool / agent settings2 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
synthetic-sciences
Language
TypeScript
Category
ai-agent
Published
7/3/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/openscience.svg)](https://workflowstacks.com/skills/openscience?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.