#1111th of 33 in Data and scraping for AIFor data and documents, documents and ocr
tesseract
OCR engine and command-line tool with LSTM recognition for 100+ languages
- Stars
- 77.3k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- C++
72,929 on 10 Apr 202677,284 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Tesseract is a C++ OCR engine (libtesseract) with a tesseract command-line program. Version 4 and later use an LSTM line-recognition engine, and the legacy Tesseract 3 engine is available with --oem 0. It reads PNG, JPEG and TIFF through Leptonica and writes plain text, hOCR, PDF, TSV, ALTO and PAGE.
Who it is for: Developers and sysadmins adding OCR to scripts or applications
Ranked among open-source alternatives to Apify (#10 of 10) and LlamaParse (#9 of 10).
Strengths
- Recognizes more than 100 languages with UTF-8 support using downloadable traineddata files
- Outputs plain text, hOCR, PDF, invisible-text PDF, TSV, ALTO and PAGE
- C and C++ APIs plus a CLI; wrappers for other languages are listed in the docs
- Can be trained for additional languages; Apache-2.0 licensed
Weaknesses
- No GUI included; third-party front-ends are needed
- Accuracy depends on input image quality; preprocessing is often required
- Leptonica opens images only, not documents like PDF
- Legacy engine mode needs separate legacy-compatible traineddata files
What it needs
- no GPU
- Needs Leptonica, traineddata files
- Models: LSTM traineddata, legacy Tesseract 3 traineddata
Quick answers
Is tesseract open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does tesseract need a GPU?
No, it runs without one.
Also in Data and scraping for AI
See all 33| Rank | Project | Score |
|---|---|---|
| 1 | mineruDocument parser that converts PDFs, images and Office files to Markdown and JSON | 94 out of 100 |
| 2 | doclingPython library and CLI that converts PDFs, Office files and more into structured text | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 87 out of 100 |
| #4 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 86 out of 100 |
| #5 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 85 out of 100 |