About Runemic: OCR for the scripts and documents most OCR reads badly.

Runemic Labs builds OCR for what standard OCR handles badly: non-Latin scripts, old scans, handwriting and unusual layouts.

日本語فارسیहिन्दीFraktur

Rune + Numeric

Rune is writing and symbols. Numeric is data and computation. Runemic is where the two meet: turning documents into data.

Our logo is the rune ᚱ (the letter R) inside a scanner's frame. The corners are data points, and the line across it is the scan.

Runemic is a small company building OCR models, software and scanning tools. We're starting with multilingual OCR and an API, then moving into document processing and digitization.

Models first

Everything else depends on the models, so we start there. The API (in preview), Scan to PDF and Split a receipt already run on preview models and move to Rune-1 when it launches; then come digitization services and scanning hardware.

  1. NowRune-1 OCR modelsRuneBench, open · API preview, Scan to PDF and Split a receipt live
  2. NextRune-1 APIScan to PDF and Split a receipt on Rune-1
  3. LaterLibrary digitizationScanning hardware

How we work

Open weights where we can

We publish models, with their evaluation code, when the licence, the training data and the economics allow it.

Measure things

We benchmark on test pages with known text, rendered and photographed, and report accuracy for each script and document type in RuneBench, including where we're weak.

Don't pretend OCR is perfect

OCR makes mistakes. You should be able to see them, measure them and correct them, so we keep the output easy to check, and Rune-1 will return a confidence score for each line.

Your documents stay yours

We don't train on what you send us, and we offer ways to run the models on your own machines.

Work with us

Working with documents, looking after an archive, or want to help? Write to us.

hello@runemic.com