DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to use MinerU: what you can do with it

What is MinerU? MinerU turns PDFs, images and office documents into LLM-ready Markdown and JSON. Version 4 adds four parsing tiers (Flash, Basic, Standard, Advanced), a local document library with search and stable citation locators for page and block continuation, a Python SDK, a V1 API, a Gradio WebUI and an agent skill, with CPU inference plus automatic GPU acceleration on Intel, AMD, NVIDIA and Apple Silicon.

How do I use it? Install MinerU 4.x in a Python 3.11 to 3.14 virtual environment with uv, as the Install Manually section of the README shows; then run mineru-kit hardware detect to see your devices and get a tier recommendation; For a quick read of a document, run mineru parse document.pdf --json, which defaults to the first 10 PDF pages. 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?

3 use cases

Quick start with MinerU

  1. Check you have what it needs: Python 3.11 to 3.14 in a virtual environment; Windows, Linux or macOS; CPU works, compatible GPUs are used automatically; Model downloads for the tier you choose.
  2. Open opendatalab/MinerU on GitHub and read the README and license.
  3. Install MinerU 4.x in a Python 3.11 to 3.14 virtual environment with uv, as the Install Manually section of the README shows
  4. Run mineru-kit hardware detect to see your devices and get a tier recommendation
  5. For a quick read of a document, run mineru parse document.pdf --json, which defaults to the first 10 PDF pages
  6. For a full conversion of all pages, use the stateless mineru-kit parse command

These steps come from our top use case, Parse a hard PDF into Markdown on your own machine, 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 opendatalab/MinerU

Add Deduped to Claude Code once

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

Cursor, ChatGPT, others

Best AI repos for Research

About this repo

  • Who it is forDevelopers and AI agent users who need high-quality parsing of complex PDFs and a searchable local library of parsed documents.
  • Why it is hot83k stars, talked about in 2 AI sources we track
  • LanguagePython
  • Sourcegithub.com/opendatalab/MinerU ยท Back to Hot repos

Requirements

  • Python 3.11 to 3.14 in a virtual environment
  • Windows, Linux or macOS; CPU works, compatible GPUs are used automatically
  • Model downloads for the tier you choose
  • Optional: Node.js for npx to install the agent skill

Add this badge to your README

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

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/opendatalab/MinerU.svg)](https://dedupedai.com/use-cases/opendatalab-mineru/?utm_source=github&utm_medium=badge&utm_campaign=opendatalab-MinerU)

HTML 

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

A static image, no tracking script. About the badge

Questions about MinerU

What is MinerU?

MinerU turns PDFs, images and office documents into LLM-ready Markdown and JSON. Version 4 adds four parsing tiers (Flash, Basic, Standard, Advanced), a local document library with search and stable citation locators for page and block continuation, a Python SDK, a V1 API, a Gradio WebUI and an agent skill, with CPU inference plus automatic GPU acceleration on Intel, AMD, NVIDIA and Apple Silicon. It is an open-source project on GitHub: https://github.com/opendatalab/MinerU.

How do I use MinerU?

Install MinerU 4.x in a Python 3.11 to 3.14 virtual environment with uv, as the Install Manually section of the README shows; then run mineru-kit hardware detect to see your devices and get a tier recommendation; For a quick read of a document, run mineru parse document.pdf --json, which defaults to the first 10 PDF pages. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is MinerU for?

Developers and AI agent users who need high-quality parsing of complex PDFs and a searchable local library of parsed documents.

What can I do with MinerU?

3 use cases so far, for example: Parse a hard PDF into Markdown on your own machine; Let your agent read long documents page by page; Search inside your parsed documents from Python. Each has steps and a copy-paste agent prompt.

What do I need to run MinerU?

Python 3.11 to 3.14 in a virtual environment; Windows, Linux or macOS; CPU works, compatible GPUs are used automatically; Model downloads for the tier you choose; Optional: Node.js for npx to install the agent skill.

What are alternatives to MinerU?

Other hot AI repos in Research: Sam2, Docling, LightRAG, Ragflow, Markitdown.

Is MinerU 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.