Updated

PyMuPDF

Python bindings for the MuPDF engine for fast PDF text, image and table extraction, with PyMuPDF4LLM for Markdown output.

76 open-source projects declare PyMuPDF in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostable

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use PyMuPDF

What PyMuPDF is used for

Document Parsing · Plain text extraction →Very fast PDF text, image and table extraction in Python, with PyMuPDF4LLM for Markdown output.Trade-off: AGPL-licensed, so closed-source products need a commercial license from Artifex.
Reducto11Unstructured1Carbon1Docling0MarkItDown0PyMuPDF0Makers' products on each, for document parsing

PyMuPDF vs the alternatives makers chose

OptionMakers' productsOpen source
Reducto11 85%No
Carbon1 8%No
Unstructured1 8%Yes
PyMuPDF0 0%Yes

For document parsing: how many of the 13 makers' products we know the document parsing of chose each option.

When to use PyMuPDF, and when not

Pick PyMuPDF if

Something else fits better if

  • You want Markdown from many file types with one local tool: MarkItDown or Docling.
  • Layout and tables matter and documents must stay on your own machines: Docling or Marker.
  • Your inputs mix PDFs, emails, HTML and office files and you may move to a hosted API later: Unstructured.
  • Scans, dense tables or forms where a parsing error means a wrong answer: Reducto or LlamaParse or Mistral AI.
From each decision's guide, written from what makers' products chose and why.

Who uses it

No maker's live product on record yet, and 76 open-source projects that declare it in their code.

We haven't found a maker's live product that uses PyMuPDF yet — only the open-source projects below, which declare it in their code.

Aix-DB
Aix-DBAix-DB 基于 LangChain/LangGraph 框架,结合 MCP Skills 多智能体协作架构,实现自然语言到数据洞察的端到端转换。Document ParsingIn its code · source ↗
LandPPT
LandPPT一个基于LLM的演示文稿生成平台,能够自动将文档内容转换为专业的PPT演示文稿。平台支持多种AI模型,提供丰富的模板和样式选择,让用户能够创建高质量的演示文稿。Document ParsingIn its code · source ↗
MathModelAgent
MathModelAgent🤖📐专为数学建模设计的 Agent & skills ,自动完成数学建模,生成一份完整的可以直接提交的论文。 An Agent Designed for Mathemati…Document ParsingIn its code · source ↗

Open source: a project that declares PyMuPDF as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

23 of the 54 open-source products built with PyMuPDF that were worked on in the last 180 days keep instruction files for coding agents — 43%, against 53% of all the projects we read. AGENTS.md is in 10, CLAUDE.md in 17.

1,016words in the median file
uvthe package manager most named, in 9 of 19 files
79%say how to test a change
Named more in these files than in other projects' — in how many of the 19:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to PyMuPDF

All alternatives by situation →

Questions makers ask about PyMuPDF

What are the alternatives to PyMuPDF?

For document parsing, the other options makers' products we track chose most are Reducto (11), Carbon (1), Unstructured (1). Open source or self-hostable among them: Unstructured. Each alternative, with the situation it fits, is on the PyMuPDF alternatives page.

When should you use PyMuPDF?

You only need the text out of born-digital PDFs, fast and free (document parsing). Something else fits better if: you want Markdown from many file types with one local tool, pick MarkItDown or Docling; Layout and tables matter and documents must stay on your own machines, pick Docling or Marker.

Is PyMuPDF open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with PyMuPDF?

No llms.txt, official MCP server or CLI found yet.

Who uses PyMuPDF?

No maker's live product we track yet; 76 open-source projects declare it in their code. source ↗