ocrs

Web · Windows · Mac · Linux · Self-hosted

Visit site Alternatives

Freedom report

One barScore 5.3

Free tierNo free tier on record
Open codeNo open-source code on record
Runs widely4 of 6 device platforms
DocumentedThinly documented

ocrs is ranked #13 of 27 in OCR API software on Freedom251. It runs on Linux, macOS, Self-hosted, Web, Windows.

Compared on OCR API software

Structure extraction: Yes
SDK languages: Rust, C

Best ocrs alternatives

See all 20

Two bars OCR.space Free tier No. 1$30/mo6.8 Two bars Tesseract OCR Free tier No. 2Free6.8 Two bars OCRmyPDF Free tier No. 3Free6.5 One bar PaddleOCR Free tier No. 4Free6.5 Two bars Veryfi Invoices OCR API Free tier No. 5$500/mo6.5 No signal Amazon Textract AnalyzeExpense Paid plans No. 6$0.01/mo6.4

The record

Purpose: ocrs is a Rust library and command line tool for extracting text from images using OCR.
Image types: The project aims to handle scanned documents, photos containing text, and screenshots with less preprocessing than older engines such as Tesseract.
Implementation: Its neural network models are trained in PyTorch, exported to ONNX, and run using the RTen engine.
Project status: The project describes itself as an early preview and cautions that it may make more errors than commercial OCR engines.
Language support: It currently recognizes the Latin alphabet, with broader language support described as planned.
Installation: The CLI can be installed with Cargo using `cargo install ocrs-cli --locked`; installing it requires Rust and Cargo.
Clipboard input: An optional `clipboard` feature enables OCR on images from the system clipboard.
Output options: The CLI can save extracted text, return text and layout information as JSON, or create an annotated image showing detected words and lines.
Automatic model download: On first run, the CLI downloads required models automatically and stores them in `~/.cache/ocrs`.
Library API: The project provides an OCR engine as a Rust library for use in Rust applications.
C interface: The `ocrs-capi` component exposes a C ABI that can create an engine from model files or memory buffers and return recognized text, including lines with bounding boxes.
Platform support: The project says it is intended to compile and run across platforms, including WebAssembly.
Model data: The project says it uses open and liberally licensed datasets, and links to a separate repository with model, dataset, and custom training details.
License: The repository lists Apache-2.0 and MIT licenses.

Where it ranks on Freedom251

Best OCR API Software in 2026#13 of 27

Is ocrs yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote ocrs

Sources

github.com/robertknight/ocrs· checked 5 Oct 2026
github.com/robertknight/ocrs/tree/main/ocrs· checked 5 Oct 2026
github.com/robertknight/ocrs/tree/main/ocrs-capi· checked 5 Oct 2026