# datalab-to/indra

> A 1M-parameter CPU OCR model that turns PDFs and images into markdown, plain text, or JSON with boxes, layout labels, and reading order. Runs on ONNX Runtime without PyTorch, up to 49 pages/s.

- Magnitude: 5.7 out of 10 — Early signal
- Stars: 117 total · +20 stars measured 2026-10-14, 09:21–11:47 UTC, ≈ 50 by evening
- Star trust: star growth looks organic
- Category: Data & analytics · Language: Python · License: Apache-2.0 · Created: 2026-10-13 · Last push: 2026-10-13
- GitHub: https://github.com/datalab-to/indra · Homepage: https://www.datalab.to · Page: https://gitnova.dev/en/r/datalab-to/indra

## Useful for

- Convert a batch of PDFs to markdown with indra-ocr *.pdf --out results/
- Extract lines, boxes, and block labels from a scan as JSON for downstream processing
- Run the local web viewer to compare output against Tesseract

## Why it’s here

- Star-counter measurements on 2026-10-14 (UTC), 09:21–11:47: 97 → 117 stars (+20). This is the change over that interval.
- Estimated end-of-day forecast: about +50 stars, using observed gains and the previous day.
- The repository is 1 day old and already has 117 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #162.
- Hacker News: “Indra OCR: a 1M-parameter OCR model that reads 49 pages per second on CPU” — 35 points, 16 h ago.
- About 14 forks a day — people are taking the code.
- Recent forks include notable developers: @mbrukman (397 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 9
- Issues and pull requests: 3
- Watchers: 0
- Average over the last week: 67 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 11
- Latest release: v0.3.1 (2026-10-13)

## Stars per day, last 2 days (oldest → newest, today is partial)

2026-10-13 … 2026-10-14: 83, 20

## Hacker News

- Indra OCR: a 1M-parameter OCR model that reads 49 pages per second on CPU — 35 points, 0 comments: https://news.ycombinator.com/item?id=50077166

## Spotted in now

- Top new repositories this week: #162

## More in this category

1. **opengeos/RustGIS** — 6.8 · Early signal · Data & analytics · Rust · +119 stars measured 2026-10-14, 00:37–11:47 UTC, ≈ 300 by evening
   RustGIS is a free, open-source GIS written in pure Rust for mapping, analyzing and sharing geospatial data. It runs natively on Windows, macOS and Linux as well as in the browser via WebAssembly, and it supports over 1,000 geoprocessing…
   Full card: https://gitnova.dev/en/r/opengeos/RustGIS.md
2. **bilawalsidhu/gods-eye-view** — 5.8 · Breakout · Data & analytics · JavaScript · +762 stars measured 2026-10-14, 00:37–11:47 UTC, ≈ 1,558 by evening
   A browser-based spy-satellite simulator on a photorealistic 3D globe that unifies public feeds: aircraft, ships, satellites, earthquakes, cameras, and traffic. Runs locally, with each layer as a separate module.
   Full card: https://gitnova.dev/en/r/bilawalsidhu/gods-eye-view.md
3. **lvzuojing/mcd-wrapped** — 4.3 · Early signal · Data & analytics · Python · +27 stars measured 2026-10-14, 01:20–11:49 UTC, ≈ 54 by evening
   A set of Python scripts on top of McDonald's MCP: probing responses of 35 tools, a personal yearly order report, and public menu analytics with lottery expected-value calculation.
   Full card: https://gitnova.dev/en/r/lvzuojing/mcd-wrapped.md
4. **HelixDB/helix-foundry** — 4.1 · Cooling · Data & analytics · TypeScript · +38 stars measured 2026-10-14, 00:38–11:49 UTC, ≈ 73 by evening
   A local-first data workspace on HelixDB and DuckDB: connects databases, Stripe, WorkOS, PostHog, files and APIs, builds one ontology across them and answers questions about your data, running on your own computer.
   Full card: https://gitnova.dev/en/r/HelixDB/helix-foundry.md
5. **feng141368-cyber/PlayerVoice-GameAnalysis-CN** — 3.8 · Early signal · Data & analytics · Python · +12 stars measured 2026-10-14, 00:39–11:50 UTC, ≈ 30 by evening
   A game research pipeline that resolves multilingual titles, gathers official facts and public community evidence, and turns them into traceable insights for players, creators, and analysts.
   Full card: https://gitnova.dev/en/r/feng141368-cyber/PlayerVoice-GameAnalysis-CN.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-14 12:04 UTC, updated every 30 minutes.