Source: https://seerepo.com/compare/opendatalab/MinerU/vs/unclecode/crawl4ai
Markdown source: https://seerepo.com/compare/opendatalab/MinerU/vs/unclecode/crawl4ai.md
Description: MinerU and crawl4ai share 8 technologies: FastAPI, aiosqlite, SQLite, uvicorn, Rich, pillow, beautifulsoup4, and Pydantic. Both are written in Python.

# MinerU vs crawl4ai

MinerU and crawl4ai share 8 technologies: FastAPI, aiosqlite, SQLite, uvicorn, Rich, pillow, beautifulsoup4, and Pydantic. Both are written in Python.

- [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.
- [unclecode/crawl4ai](https://seerepo.com/r/unclecode/crawl4ai): Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.

## What they share and what sets them apart

- In common: FastAPI, aiosqlite, SQLite, uvicorn, Rich, pillow, beautifulsoup4, Pydantic
- Only in MinerU: Hugging Face, OpenAI, Gradio, onnxruntime, ModelScope, ONNX, tokenizers, mineru, pypdfium2, loguru
- Only in crawl4ai: Redis, AIOHTTP, anyio, pyjwt, rank-bm25, MCP, lxml, pypdf, email-validator, Gunicorn, psutil, prometheus-fastapi-instrumentator

## Side by side

| | MinerU | crawl4ai |
|---|---|---|
| Size | 158,109 lines written, 375 code files | 176,861 lines written, 105 code files |
| Who writes it | 12.6% of its commits signed by AI. With GitHub Copilot, Claude Code, and Codex | 4.4% of its commits signed by AI. With Claude Code, Factory, Cursor, CodeRabbit, and Devin |
| Activity | Last push November 4, 2026, 5,064 commits, 83,126 stars | Last push November 4, 2026, 1,446 commits, 86,895 stars |
| Tests | 236 test files. 2.1% of its code files have a test that imports them | 286 test files. 56.2% 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, MinerU or crawl4ai?

crawl4ai, with 176,861 lines written; MinerU has 158,109.

The proof: [unclecode/crawl4ai's code at commit cae74b2](https://github.com/unclecode/crawl4ai/tree/cae74b203a33994f7e13b9052c3b0d5c93daa0e6)

### Which has more GitHub stars, MinerU or crawl4ai?

crawl4ai, with 86,895 stars; MinerU has 83,126.

The proof: [unclecode/crawl4ai on GitHub](https://github.com/unclecode/crawl4ai)

### Which has more tests, MinerU or crawl4ai?

crawl4ai, with 286 test files; MinerU has 236.

The proof: [unclecode/crawl4ai's code at commit cae74b2](https://github.com/unclecode/crawl4ai/tree/cae74b203a33994f7e13b9052c3b0d5c93daa0e6)

### Which was updated more recently, MinerU or crawl4ai?

Both got their last push on November 4, 2026.

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

### Which has more commits signed by AI, MinerU or crawl4ai?

MinerU: an AI signed 12.6% of its commits, with GitHub Copilot, Claude Code, and Codex; in crawl4ai, 4.4%.

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

## Sources

- opendatalab/MinerU: Read on November 4, 2026, at commit 8cd0842 (https://github.com/opendatalab/MinerU/tree/8cd08422055858f55a64dff79f942318b51b96cc)
- unclecode/crawl4ai: Read on November 4, 2026, at commit cae74b2 (https://github.com/unclecode/crawl4ai/tree/cae74b203a33994f7e13b9052c3b0d5c93daa0e6)

## 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.