Source: https://seerepo.com/compare/datalab-to/surya/vs/opendatalab/MinerU
Markdown source: https://seerepo.com/compare/datalab-to/surya/vs/opendatalab/MinerU.md
Description: surya and MinerU share 6 technologies: Hugging Face, OpenAI, pillow, beautifulsoup4, pypdfium2, and Pydantic. Both are written in Python.

# surya vs MinerU

surya and MinerU share 6 technologies: Hugging Face, OpenAI, pillow, beautifulsoup4, pypdfium2, and Pydantic. Both are written in Python.

- [datalab-to/surya](https://seerepo.com/r/datalab-to/surya): OCR, layout analysis, reading order, table recognition in 90+ languages
- [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: Hugging Face, OpenAI, pillow, beautifulsoup4, pypdfium2, Pydantic
- Only in surya: torch, transformers, torchvision, filetype
- Only in MinerU: FastAPI, aiosqlite, SQLite, uvicorn, Rich, Gradio, onnxruntime, ModelScope, ONNX, tokenizers, mineru, loguru

## Side by side

| | surya | MinerU |
|---|---|---|
| Size | 16,145 lines written, 93 code files | 158,109 lines written, 375 code files |
| Who writes it | 0.3% of its commits signed by AI. With Claude Code | 12.6% of its commits signed by AI. With GitHub Copilot, Claude Code, and Codex |
| Activity | Last push October 29, 2026, 799 commits, 21,579 stars | Last push November 4, 2026, 5,064 commits, 83,126 stars |
| Tests | 16 test files. 22.6% 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, surya or MinerU?

MinerU, with 158,109 lines written; surya has 16,145.

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

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

MinerU, with 83,126 stars; surya has 21,579.

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

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

MinerU, with 236 test files; surya has 16.

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

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

MinerU: its last push was on November 4, 2026, and surya's on October 29, 2026.

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

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

MinerU: an AI signed 12.6% of its commits, with GitHub Copilot, Claude Code, and Codex; in surya, 0.3%.

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

## Sources

- datalab-to/surya: Read on November 5, 2026, at commit 9d5aadf (https://github.com/datalab-to/surya/tree/9d5aadfebb07939755c24e8a80d0e61b3be80895)
- 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.