Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
aipoch/open-science
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
- Stars
- 5,557
- +7 days
- —
- Forks
- 561
- Language
- TypeScript
- License
- Apache-2.0
- Last push
- 22 Nov 2026
Summary
Summary written by AI from the README; it may be imprecise.This local-first AI research workbench provides a desktop app and CLI for reproducible scientific research and agent workflows. It supports Python and R notebook execution, extensible skills, and full provenance tracing through portable research packages. Developers can also connect external agents like Claude Code via its built-in MCP server.
Use it when
- Conducting reproducible scientific research with Python or R notebooks and full provenance tracking
- Connecting Claude Code or other local agents to a scientific workbench using MCP
- Sharing self-contained research packages that let peers inspect code, inputs, and verification evidence
Install
npm install --global @aipoch/open-scienceCommands quoted from the repo's README. Read the README before running them.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.