MinerU

MinerU is a document parser that turns PDFs and Office files into clean markdown or JSON for AI workflows.

What it is good for

  • Converting PDFs into text an AI can read
  • Extracting tables and formulas from long documents
  • Running OCR on scanned documents and images
  • Preparing Word, PowerPoint, and Excel files for AI tools

At a glance

Who it is for
Setup
Guided command-line setup

Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.

Cost
Free and open source
Type
Agent app
Tasks
Works with
Claude Code, Codex

Momentum

Rank this week
Not ranked yet
Best rank
None yet
GitHub stars
82,984

GitHub numbers as of Nov 2, 2026. Updated weekly.

80.1k 81.7k 83.2k Sep 24, 2026 Nov 2, 2026
GitHub stars for MinerU: 80,317 on Sep 24, 2026, 82,984 on Nov 2, 2026. Source: GitHub.

Official links

Setup steps are on the official pages. We do not repeat them here, since they change.

Questions

Is MinerU free?
Yes. It is free and open source.
Do I need to know how to code to use MinerU?
You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
What does MinerU work with?
According to its own documentation, it works with Claude Code and Codex.
What is MinerU good for?
Converting PDFs into text an AI can read, extracting tables and formulas from long documents, running OCR on scanned documents and images, and preparing Word, PowerPoint, and Excel files for AI tools.

Similar agents

  • kordoc

    kordoc is a command-line tool and MCP server that converts Korean documents (HWP, HWPX, PDF, Office files) to Markdown for people working with government and office paperwork.

  • Firecrawl

    Firecrawl is an API that searches the web and pulls clean page content for AI agents and apps.

  • Scrapling

    Scrapling is a Python web scraping framework that collects data from websites, including JavaScript-heavy and bot-protected ones, for developers.

  • OpenBB

    OpenBB is an open data platform that connects financial data sources to Python, dashboards, and AI agents for analysts.

  • OfficeCLI

    OfficeCLI is a command-line tool that lets AI agents read, edit, and create Word, Excel, and PowerPoint files without Office installed.

  • Nanobrowser

    Nanobrowser is a Chrome extension that runs an AI agent in your own logged-in browser to carry out web tasks for you.

Last updated Nov 2, 2026. Tracked since Oct 28, 2026. Parts of this summary required judgment because the source material was brief. The summary was written by an AI model from the project's own description and checked against our copy rules. Spotted an error? Tell us.