# robertknight/ocrs

Rust library and CLI tool for OCR (extracting text from images)

Repository: https://github.com/robertknight/ocrs
Canonical: https://ross.abutalabs.com/products/ocrs
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: computer-vision, machine-learning, ocr
Last push: 2026-08-02T06:24:56+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 69
- inputs: {"age_days": 974, "days_push": 31, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1875, forks 90 (observed 2026-08-28T04:05:47.494732+00:00)

## What it is
Ocrs is a Rust library and CLI tool for optical character recognition that extracts text from images such as scanned documents, photos, and screenshots. It uses neural network models (trained in PyTorch, exported to ONNX and run via the RTen engine) and is designed to compile across many platforms including WebAssembly.

## Use cases
- extract text from images with OCR
- convert scanned documents to text
- read text from screenshots
- run OCR in WebAssembly in the browser
- get text layout positions from images as JSON
- replace Tesseract with a modern ML-based OCR engine

## When to choose
- you need OCR in a Rust project or as a standalone CLI
- you want easy cross-platform compilation including WebAssembly
- you need a permissively licensed OCR engine trained on open datasets
- you want JSON output with word and line layout information

## When to avoid
- you need high accuracy comparable to commercial OCR engines
- you need to recognize non-Latin scripts or languages other than English
- you need a battle-tested, mature OCR solution

## Facets
- artifact type: library
- maturity: active
- function: ocr, image-processing, machine-learning, cli
- domain: computer-vision, machine-learning
- platform: rust, cross-platform, wasm, cli
- tags: ocr, text-extraction, onnx, neural-networks, rust-library, text-processing

## Member repositories
- robertknight/ocrs (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:47.494732+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:14:46.947478+00:00, confidence not recorded.
  - readme: https://github.com/robertknight/ocrs (fetched 2026-08-28T04:05:47.494732+00:00, sha 3a8c3740e2b0)
  - registry_crates: https://crates.io/api/v1/crates/ocrs (fetched 2026-08-29T10:53:36.950528+00:00, sha ed3f514317ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.