OXR
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
43Today’s rankDown 3 places since yesterday
OXR launched on 5 October 2026. It ranked #43 on Daily Launch on 30 October 2026 with a Launch Score of 45, from +287 stars today on GitHub. It moved down 3 places from the day before.
Visit site287 stars on GitHub today
What is OXR?
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training. OXR (Optical Everything Recognition) is an open-source model from the SoMark team. It turns PDFs and document images into Agent-Friendly data in Markdown or JSON, with layout coordinates included.
From its README on GitHub
OXR is a repo by SoMarkAI on GitHub. It is written in Python.
How to get OXR
Get it from its repository on GitHub.
