BigHugger
GH Repository · aipoch

open-science

AIPOCH Open-Science is an open-source, local-first, model-agnostic AI research workbench for macOS, Windows, and Linux, with scientific agents, Python/R notebooks, data connectors, and reproducible provenance.

stars
4,346
30-day movement
-63-21/day
Related entries
60
Connections
2
typescriptresearch-workbenchelectronbioinformaticsai-workbenchnodemcpai-for-sciencelocal-firstreproducible-researchmcp-servermodel-agnosticopen-sciencepythonresearch-softwarescientific-airlinuxai-researchdesktop-appmacoswindowsTypeScriptclaude-science-alternative

AIPOCH Open-Science is a described open-source, local-first, model-agnostic AI research workbench for macOS, Windows, and Linux. Per its own description it combines scientific agents, Python/R notebooks, data connectors, and reproducible provenance; the codebase is TypeScript with an Electron desktop app and an MCP server role.

You want a desktop AI research workbench that keeps work local-first and model-agnostic while tying agents, Python/R notebooks, and provenance together.

Use it to

  • Run scientific AI agents from a local desktop app
  • Work with Python and R notebooks in one place
  • Connect data sources through its data connectors
  • Track reproducible provenance for analyses
  • Serve research tools via its MCP server role

For Researchers and scientists doing AI-assisted, reproducible analysis

Role
mcp-server
Language
TypeScript
Licence
Apache-2.0
Forks
274
Open issues
17
Last push
2026-09-17
Latest release
v0.1.0 · 2026-07-10
topicsai-for-sciencelocal-firstreproducible-researchmcpresearch-workbenchnotebooks