RepoAlerts
SponsorGet alerts

SoMarkAI/OXR

Model

Get alerts like thisView on GitHubWebsiteShare on X

Can I trust it?

Be careful with this one.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 2 days ago.

  • Licence Careful

    No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

An open-source document parsing model that converts PDFs and document images into Markdown or JSON with layout coordinates. It recognizes 13 element types, including tables, formulas and chemical structures, and separates layout analysis into a pluggable module that can be…

Who it's for

Developers and teams building pipelines that turn documents into structured data for AI agents or RAG systems

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up SoMarkAI/OXR in my project. Follow its README: https://github.com/SoMarkAI/OXR. Explain each step and check it is safe before running anything.

Read the README

Star curve

110From 0 to 110 stars between 5 Oct 2026 and 22 Oct 2026.

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

18,913 GitHub repos watched and ranked every hour. Figures as of 22 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![SoMarkAI/OXR on RepoAlerts](https://repoalerts.com/badge/SoMarkAI/OXR.svg)](https://repoalerts.com/repo/SoMarkAI/OXR?ref=badge)
Share on X
  • datalab-to/indra

    Indra OCR is a CPU-based OCR tool that converts PDFs and images into markdown, text, or JSON with line boxes, layout labels and reading order. It runs on ONNX Runtime without PyTorch or a GPU and supp

    CLI toolPython · 892 stars · +601 this week · 9 days old

  • chenxiachan/textfold

    A Python tool that folds papers, web pages, files and AI replies into five levels of detail, from the full text to a one-word topic map. It runs locally and can connect to a model you already have, wi

    Python · 416 stars · +249 this week · 17 days old

  • Nutlope/gloss

    An open source reader for articles and PDFs. You select a line, ask a question, and receive a cited answer in the margin, generated by an open model on Together AI. Optional web search via Exa and lib

    Web & UITypeScript · 302 stars · +134 this week · 13 days old

  • fatsearch/fatsearch

    A Rust command-line tool and MCP server that fetches web pages for AI agents, including JavaScript-rendered pages and PDFs, and stores them as clean Markdown navigable by outline and section ids. Opti

    CLI toolAI agentsRust · 48 stars · +48 this week · 5 days old

  • YuriyLin/PaperRead

    A personal research workspace for reading academic papers in a Traditional Chinese interface. It combines topic and venue search over OpenAlex, DBLP and Crossref, a candidate list, a reading kanban, s

    Python · 305 stars · +302 this week · 12 days old

  • DeepanshuMishraa/leaf

    A terminal reader for PDFs, markdown files and web articles. It converts PDFs to markdown with inline images, renders markdown with GitHub extensions, and extracts article text from URLs. It supports

    CLI toolRust · 40 stars · +40 this week · 5 days old