Local, open-source PDF and document parser in Rust with text extraction, bounding boxes, Markdown/JSON output, and optional OCR.
12.9K885RustApache-2.0Updated 6 days ago
3 alternatives
Best open-source alternatives to Amazon Textract (2026)
Looking for a free, open-source alternative to Amazon Textract? These 3 projects can replace it. Each one is reviewed by a human and explained in plain words, so you can compare stars, license and maintenance at a glance.
Quick comparison
| Project | Stars | License | Last commit |
|---|---|---|---|
| run-llama/liteparse | ★ 12.9K | Apache-2.0 | 6 days ago |
| deepdoctection/deepdoctection | ★ 3.3K | Apache-2.0 | last month |
| CatchTheTornado/text-extract-api | ★ 3.2K | MIT | 10 months ago |
A Python library for document AI that combines layout analysis, table recognition, OCR and document or token classification into configurable pipelines.
3.3K200PythonApache-2.0Updated last month
Self-hosted API that converts PDFs, images and Office documents into Markdown or structured JSON using OCR and Ollama-hosted LLMs, with optional PII removal.
3.2K279PythonMITUpdated 10 months ago
FAQ
- Is there a free, open-source alternative to Amazon Textract?
- Yes. The most popular open-source alternatives to Amazon Textract on Repolode are liteparse, deepdoctection, text-extract-api.
- Which Amazon Textract alternative should I choose?
- liteparse has the most GitHub stars and is released under Apache-2.0. Compare the license and last commit of each option in the table above before choosing.