robertknight/ocrs

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1875 stars · 90 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity active

ocr image-processing machine-learning cli computer-vision machine-learning rust cross-platform wasm cli ocr text-extraction onnx neural-networks rust-library text-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="robertknight/ocrs")