Source: https://seerepo.com/compare/ocrmypdf/OCRmyPDF/vs/opendatalab/MinerU
Markdown source: https://seerepo.com/compare/ocrmypdf/OCRmyPDF/vs/opendatalab/MinerU.md
Description: OCRmyPDF and MinerU share 4 technologies: Rich, pillow, pypdfium2, and Pydantic. Both are written in Python.

# OCRmyPDF vs MinerU

OCRmyPDF and MinerU share 4 technologies: Rich, pillow, pypdfium2, and Pydantic. Both are written in Python.

- [ocrmypdf/OCRmyPDF](https://seerepo.com/r/ocrmypdf/OCRmyPDF): OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
- [opendatalab/MinerU](https://seerepo.com/r/opendatalab/MinerU): Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

## What they share and what sets them apart

- In common: Rich, pillow, pypdfium2, Pydantic
- Only in OCRmyPDF: fpdf2, pdfminer.six, pikepdf, uharfbuzz
- Only in MinerU: FastAPI, aiosqlite, SQLite, Hugging Face, OpenAI, uvicorn, Gradio, onnxruntime, ModelScope, ONNX, tokenizers, mineru, beautifulsoup4, loguru

## Side by side

| | OCRmyPDF | MinerU |
|---|---|---|
| Size | 50,888 lines written, 94 code files | 158,109 lines written, 375 code files |
| Who writes it | 2% of its commits signed by AI. With Aider and Claude Code | 12.6% of its commits signed by AI. With GitHub Copilot, Claude Code, and Codex |
| Activity | Last push October 25, 2026, 4,300 commits, 35,254 stars | Last push November 4, 2026, 5,064 commits, 83,126 stars |
| Tests | 97 test files. 64.9% of its code files have a test that imports them | 236 test files. 2.1% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, OCRmyPDF or MinerU?

MinerU, with 158,109 lines written; OCRmyPDF has 50,888.

The proof: [opendatalab/MinerU's code at commit 8cd0842](https://github.com/opendatalab/MinerU/tree/8cd08422055858f55a64dff79f942318b51b96cc)

### Which has more GitHub stars, OCRmyPDF or MinerU?

MinerU, with 83,126 stars; OCRmyPDF has 35,254.

The proof: [opendatalab/MinerU on GitHub](https://github.com/opendatalab/MinerU)

### Which has more tests, OCRmyPDF or MinerU?

MinerU, with 236 test files; OCRmyPDF has 97.

The proof: [opendatalab/MinerU's code at commit 8cd0842](https://github.com/opendatalab/MinerU/tree/8cd08422055858f55a64dff79f942318b51b96cc)

### Which was updated more recently, OCRmyPDF or MinerU?

MinerU: its last push was on November 4, 2026, and OCRmyPDF's on October 25, 2026.

The proof: [opendatalab/MinerU's commits on GitHub](https://github.com/opendatalab/MinerU/commits)

### Which has more commits signed by AI, OCRmyPDF or MinerU?

MinerU: an AI signed 12.6% of its commits, with GitHub Copilot, Claude Code, and Codex; in OCRmyPDF, 2%.

The proof: [the commits each tool signed in opendatalab/MinerU](https://seerepo.com/r/opendatalab/MinerU/ai)

## Sources

- ocrmypdf/OCRmyPDF: Read on November 7, 2026, at commit b457e9e (https://github.com/ocrmypdf/OCRmyPDF/tree/b457e9efa68c3a46be2470ffb222ed1bccc4dcbc)
- opendatalab/MinerU: Read on November 4, 2026, at commit 8cd0842 (https://github.com/opendatalab/MinerU/tree/8cd08422055858f55a64dff79f942318b51b96cc)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.