Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
| Date | Stars |
|---|---|
| 2026-07-31 | 2046 |
| 2026-08-03 | 2050 |
| 2026-08-06 | 2050 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
5.0
growth rate 0.00%/day
<p align="center">
<a href="https://pymupdf.io?utm_source=github&utm_medium=referral&utm_campaign=pymupdf4llm_github&utm_content=logo&utm_term=website">
<img loading="lazy" alt="PyMuPDF" src="https://pymupdf.pro/images/py-mupdf4llm-github-icon.png" width="96px" alt="PyMuPDF logo"/>
</a>
</p>
# PyMuPDF4LLM
<p align="center">
<a href="https://trendshift.io/repositories/11536" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11536" alt="pymupdf%2FPyMuPDF | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
</p>
[](https://pymupdf.readthedocs.io/en/latest/pymupdf4llm?utm_source=github&utm_medium=referral&utm_campaign=pymupdf4llm_github&utm_content=badges&utm_term=docs)
[](https://pypi.org/project/pymupdf4llm)
[](https://pypi.org/project/pymupdf4llm/)
[](https://github.com/pymupdf/pymupdf4llm/blob/master/LICENSE)
[](https://pepy.tech/projects/pymupdf4llm)
[](https://github.com/pymupdf/pymupdf4llm/stargazers)
[](https://artifex.com/discord/artifex?utm_source=github&utm_medium=referral&utm_campaign=pymupdf4llm_github&utm_content=badges&utm_term=discord)
[](https://forum.mupdf.com/c/general/4?utm_source=github&utm_medium=referral&utm_campaign=pymupdf4llm_github&utm_content=badges&utm_term=forum)
[](https://x.com/pymupdf4llm)
[](https://huggingface.co/artifex-software)
[](https://demo.pymupdf.io?utm_source=github&utm_medium=referral&utm_campaign=pymupdf4llm_github&utm_content=badges&utm_term=demo)
**Turn PDF and other documents into clean, LLM-ready data — in one line of code. No GPU, no Cloud, no Tokens required.**
PyMuPDF4LLM is a lightweight extension for [PyMuPDF](https://github.com/pymupdf/PyMuPDF) that converts documents into structured Markdown, JSON, and plain text optimised for RAG pipelines, vector embeddings, and LLM ingestion. It handles multi-column layouts, tables, images, headers, and scanned pages with automatic OCR — all powered by the MuPDF C engine.
```python
import pymupdf4llm
md = pymupdf4llm.to_markdown("research-paper.pdf")
# Feed directly into your LLM, vector store, or chunker
```
[](https://github.com/pymupdf/pymupdf4llm/)
[](https://demo.pymupdf.io?utm_source=github&utm_medium=referral&utm_campaign=pymupdf4llm_github&utm_content=body&utm_term=demo)
---
## Why PyMuPDF4LLM?
- **One import, three output formats** — Markdown, JSON, and plain text out of the box
- **No GPU, no cloud** — runs on any machine that can run Python
- **Layout-aware** — multi-column pages, reading-order reconstruction, table detection
- **Smart OCR** — automatically OCRs only the regions that need it, skipping clean text
- **Framework integrations** — drop-in support for LlamaIndex and LangChain
- **Page chunking** — chunk output by page with full metadata per chunk, ready for vector stores
- **10–250× cheaper** than vision-based LLM extraction approaches
---
## Installation
```bash
pip Excerpt of 20,814 characters
Read on GitHub
167
49
Jamie Lemon · Artifex
42
Yannick Stephan · Switzerland
10
7
5
2
2
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9892b71c70b78028, llm:Repository name and description: 'PyMuPDF4LLM' — suggests PyMuPDF integration for LLMs (PDF processing for LLM workflows). No README provided.
matched fp:9892b71c70b78028, llm:Repository name and description: 'PyMuPDF4LLM' — suggests PyMuPDF integration for LLMs (PDF processing for LLM workflows). No README provided.
matched fp:9892b71c70b78028, llm:Repository name and description: 'PyMuPDF4LLM' — suggests PyMuPDF integration for LLMs (PDF processing for LLM workflows). No README provided.