DEDUPED Hot AI repos, turned into use cases Get the Monday 5
171 stars · Python

How to use OXR: what you can do with it

What is OXR? OXR is an open-source document parsing model from the SoMark team that turns PDFs and document images into Markdown or JSON with layout coordinates.

How do I use it? Open the Online Demo at https://free-oxr.somark.ai in a browser; then upload your PDF or image file; review the parsed Markdown output and check tables and formulas against the original. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Try OXR on one document without an API key

    Upload one PDF or image to the free online demo and download the Markdown result.

    View prompt
    Using the OXR repo at https://github.com/SoMarkAI/OXR, parse <path-to-document.pdf> through the free online demo at https://free-oxr.somark.ai and save the Markdown output. Verify that the tables and formulas in the output match the original document.

  • Convert PDFs to Markdown and JSON from the command line

    Use the SoMark CLI with the free OXR endpoint to batch-convert documents to Markdown and JSON.

    View prompt
    Using the OXR repo at https://github.com/SoMarkAI/OXR, install the somark CLI and parse <path-to-document.pdf> with the base URL https://free-oxr.somark.ai/api/v1, outputting md and json to ./parsed-output/. Verify that both output files exist and that the JSON includes layout coordinates.

  • Host a private OXR parsing API on your own GPU

    Run the OXR parsing service in Docker so your documents stay on your own hardware.

    View prompt
    Using the OXR repo at https://github.com/SoMarkAI/OXR, download the OXR-1.0 weights, build the allinone Docker image, and start it on port 8000. Verify that http://localhost:8000/docs loads, then parse <path-to-document.pdf> via POST to /v1/parse/sync and save the returned Markdown.

  • Replace OXR's layout model with your own for a niche document type

    Point the OXR parsing API at a custom layout analysis service while keeping OXR for recognition.

    View prompt
    Using the OXR repo at https://github.com/SoMarkAI/OXR, set the layout_analyze_model url in config.yaml to <custom-layout-service-url> and start the parsing API. Parse <path-to-sample-document.pdf> and verify that the layout bounding boxes in the JSON output come from the custom layout service.

Quick start with OXR

  1. Check you have what it needs: A PDF or document image to parse; Python 3.12 or Node.js for the SoMark CLI, or Docker for a local service; For local hosting: Linux, an NVIDIA GPU with BF16 support, and 24GB or more of GPU memory.
  2. Open SoMarkAI/OXR on GitHub and read the README and license.
  3. Open the Online Demo at https://free-oxr.somark.ai in a browser.
  4. Upload your PDF or image file.
  5. Review the parsed Markdown output and check tables and formulas against the original. (inferred, check the README)
  6. Download the Markdown result if it looks correct.

These steps come from our top use case, Try OXR on one document without an API key, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for SoMarkAI/OXR

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

OXR alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and AI agent builders who need PDFs and scanned documents converted into structured, agent-readable data.
  • Why it is hot171 stars, launched 21 days ago, picked up by one AI source we track
  • LanguagePython
  • Sourcegithub.com/SoMarkAI/OXR · Back to Hot repos

Requirements

  • A PDF or document image to parse
  • Python 3.12 or Node.js for the SoMark CLI, or Docker for a local service
  • For local hosting: Linux, an NVIDIA GPU with BF16 support, and 24GB or more of GPU memory

Add this badge to your README

Maintain OXR? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/SoMarkAI/OXR.svg)](https://dedupedai.com/use-cases/somarkai-oxr/?utm_source=github&utm_medium=badge&utm_campaign=SoMarkAI-OXR)

HTML 

<a href="https://dedupedai.com/use-cases/somarkai-oxr/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=SoMarkAI-OXR"><img src="https://dedupedai.com/badge/SoMarkAI/OXR.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about OXR

What is OXR?

OXR is an open-source document parsing model from the SoMark team that turns PDFs and document images into Markdown or JSON with layout coordinates. It is an open-source project on GitHub: https://github.com/SoMarkAI/OXR.

How do I use OXR?

Open the Online Demo at https://free-oxr.somark.ai in a browser; then upload your PDF or image file; review the parsed Markdown output and check tables and formulas against the original. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is OXR for?

Developers and AI agent builders who need PDFs and scanned documents converted into structured, agent-readable data.

What can I do with OXR?

4 use cases so far, for example: Try OXR on one document without an API key; Convert PDFs to Markdown and JSON from the command line; Host a private OXR parsing API on your own GPU. Each has steps and a copy-paste agent prompt.

What do I need to run OXR?

A PDF or document image to parse; Python 3.12 or Node.js for the SoMark CLI, or Docker for a local service; For local hosting: Linux, an NVIDIA GPU with BF16 support, and 24GB or more of GPU memory.

What are alternatives to OXR?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is OXR safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.