---
title: "Tesseract: motor OCR open source"
description: "Motor de OCR com LSTM para extração de texto em imagens e PDFs."
canonical: "https://ronanrodrigo.dev/notes/tesseract-motor-ocr-open-source"
markdown: "https://ronanrodrigo.dev/notes/tesseract-motor-ocr-open-source.md"
last-updated: "2026-09-04"
---
## Destaques

Tesseract Open Source OCR Engine (main repository). Motor clássico de OCR com LSTM e machine learning, base comum para pipelines de extração de texto antes de agentes e RAG.

[Acesse o repositório original](https://github.com/tesseract-ocr/tesseract)
