Tesseract OCR

license

Apache-2.0(OSI)

source

public(tesseract-ocr/tesseract is the engine)

core features withheld

no — a 780-entry recursive tree carries no path matching enterprise, ee, commercial or proprietary, and no vendor sells a Tesseract edition

Apache-2.0 with no vendor and no paid edition. The 780-entry recursive tree carries no enterprise, ee or commercial path.

• https://api.github.com/repos/tesseract-ocr/tesseract/git/trees/main?recursive=1 recorded 2026-09-16

  Full untruncated recursive tree of the default branch, 780 entries. One root LICENSE. No path matches enterprise, ee, commercial or proprietary. A tree lists paths; it is cited for that and for nothing about the vendor's offerings.

• https://github.com/tesseract-ocr/tesseract recorded 2026-09-16

  The Tesseract repository page. Tesseract is maintained as a community open-source project with no vendor and no commercial edition; cited for the licence, the public source and the absence of a paid tier.

Tesseract is distributed as source and through operating-system packages rather than through a registry this map can measure, leaving GitHub stars as the only comparable adoption signal. That almost certainly understates the use of a library embedded in a very large amount of other software.

• https://github.com/tesseract-ocr/tesseract recorded 2026-09-16

  Repository page showing the star count for tesseract-ocr/tesseract.

Tesseract's LSTM engine recognizes characters and their positions in plain text, hOCR, ALTO, TSV or PDF, but recovers no reading order, tables or document structure of its own. It remains the OCR engine many other document tools build their own recognition on, even though it leaves structure recovery to whatever wraps it.

• https://github.com/tesseract-ocr/tesseract recorded 2026-09-16

  Repository page and README describing the LSTM OCR engine, its language coverage and its output formats.