# AIPOCH Open-Science is an open-source desktop app that records AI research provenance

> Original title: An Apache-2.0 app with 4.8K GitHub stars is trying to make AI-assisted science as traceable as checksummed, versioned code.

- Source: Rohan Paul
- Published: 2026-10-14T21:55:26.000Z
- Bad Influence: https://badinfluence.news/items/ksej8ypzjdkup6zupgp0bblao
- Original: https://x.com/rohanpaul_ai/status/2110489685198098844

## Summary

AIPOCH's Open-Science is a free, Apache 2.0 licensed desktop app where an AI agent reads papers, queries science databases, and runs Python or R code. Each result records its input data, code, software setup and run history, and sessions export as a .science file without API keys. A public example checked 100 references from 20 AI-written math papers, finding 88 matches, 7 minor slips, and 5 unresolved, and the file separates verdicts that rest on human notes.

## Why it matters

The post shows how a session records its inputs, code, and run history in one exportable file, making AI-assisted research results checkable by others.

## Post

An Apache-2.0 app with 4.8K GitHub stars is trying to make AI-assisted science as traceable as checksummed, versioned code.

@aipoch_ai’s Open-Science is a free, open-source desktop app where an AI agent reads papers, pulls data from science databases, writes and runs Python or R code, and saves the charts and reports, all in a single workspace on your computer.

Research is usually split across PDFs, spreadsheets, code editors and terminals, so results lose their link to the data and code behind them.

Open-Science keeps that link: every result records its input data, code, software setup and run history, and the whole session exports as a single .science file that holds the conversation, the chosen files and the evidence, minus your API keys.

A public example shows it in action: in “AI Math Citations: Do They Check Out”, the session took 5 references from each of 20 AI-written math papers and checked whether each points to a real publication.

A direct check against publication records matched 80 of the 100 and found none to be fake, and after notes the researcher added, the final count was 88 matches, 7 small slips like an online date versus a print year, and 5 unresolved.

Because the .science record keeps those 2 evidence sources apart, anyone opening it can see which verdicts rest on human notes, including all 6 positive verdicts in a smaller test of whether cited papers really back 10 specific claims.

It is model-agnostic, so it works with whichever AI model you choose (cloud providers, custom gateways, or a Claude or Codex subscription), and local-first, so projects stay on your machine by default.

The agent runs code only after you approve it, and it ships with science skills like AlphaFold2 (predicts a protein’s 3D shape) that you can extend with your own.

It is Apache 2.0 licensed and runs on macOS, Windows and Linux.
🧵1/n

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHUn2N5taYAA6q56.jpg&mode=thumb&exp=1793404800&sig=31bfe8a7a7048214)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHUn2YZiasAAFc_V.jpg&mode=thumb&exp=1793404800&sig=47f5c82fa8af206c)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHUn2Z8IaMAAme1A.jpg&mode=thumb&exp=1793404800&sig=ac8f8d69605da0a7)