Home Projects docext
docext

docext

by NanoNets · GitHub

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

# document# document-analysis# document-data-extraction# document-information-extraction
View on GitHub
⭐ Stars
2k
🍴 Forks
148
🔥 Trending
+2 this week
📜 License
Apache-2.0
Commercial use OK
📅 Created
2025
🔄 Last commit
4 mo ago
🏷️ Category
document
💻 Language
🖥️ Self-hostable
Likely
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
docext — GitHub preview card
📈 Star history
2 0322 030
2026-07-072026-07-22
📄 About

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

Frequently asked questions

What is docext?

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

Is docext open source?

docext is an open-source project. It is released under the Apache-2.0 license.

Is docext free?

Yes. docext is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?
OpenSourceAI badge — docext

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![OpenSourceAI](https://opensourceai.tech/badge.php?tool=nanonets-docext)](https://opensourceai.tech/project/nanonets-docext.html)
More badge options →
🧬 Related projects🧬 View the DNA map →