MinerU

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

opendatalab/MinerU

View on GitHub ↗

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

MinerU grew +2.3% in the last 30 days, ranks 11th of 1,539 in Memory & Knowledge (RAG), actively maintained, last commit today.

Star trajectory

122 days tracked
2026-06-2682.5k stars today2026-10-26
Momentum

+2.3% in 30d, above the Memory & Knowledge (RAG) median of +0.9%.

Maintenance

Last commit today, fresher than the median of 17d.

How it compares in Memory & Knowledge (RAG)

MinerU
82.5k
stars
+2.3% 30d
commit today
Memory & Knowledge (RAG) median
382
stars
+0.9% 30d
commit ~17d ago
Leader · markitdown
192.2k
stars
+2.8% 30d
commit 2 days ago

Ranked 11th of 1,539 by stars.

Language
Python
License
Other
Contributors
103
Forks
6.8k
Watchers
280
Open issues
13
Releases
199
Created
2024-02-29
Stars this week
+445

You've seen where MinerU stands today.

Get the moves before everyone else: the 5 Memory & Knowledge (RAG) repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain MinerU?

Claim this page to add your own call-to-action.

Claim this page