Is there an open-source alternative to AWS Textract?

Yes. PaddleOCR, Paperless-ngx are open-source document OCR alternatives to AWS Textract that you can self-host.

Can I self-host a AWS Textract alternative for free?

Each option here is open source and self-hostable. Star counts and growth are tracked live on Repository Radar.

// alternatives

Open-source alternatives to AWS Textract

2 open-source document OCR alternatives to AWS Textract we track, each self-hostable, with live GitHub metrics and a get-it block. These are our picks, not a scrape of GitHub trending. Also replaces Google Document AI, ABBYY.

💡PaddleOCR ACTIVE

PaddlePaddle/PaddleOCR

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

86k

+ 3k/mo (+4%/mo) since covered

Python

🗒️Paperless-ngx ACTIVE

paperless-ngx/paperless-ngx

A community-supported supercharged document management system: scan, index and archive all your documents

44k

+ 1k/mo (+4%/mo) since covered

Python