opendatalab/MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
About the project
MinerU is a Python tool that parses PDFs, images, and Office documents into LLM-ready Markdown/JSON. It supports OCR, layout analysis, tables and formulas, plus a local document library with search and citation locators.
Useful for
- Convert a scientific PDF paper into Markdown for an LLM pipeline
- OCR scanned documents and extract text with tables
- Install MinerU as an agent skill to read and cite local documents
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 14 stars so far today, about 40 expected by the end of the day.
- GitHub Trending Python today: #12, +62 stars.
- About 8 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 80,238
- Stars in a day
- 40
- Forks
- 6,697
- Issues and pull requests
- 4,242
- Watchers
- 280
- Language
- Python
- Latest release
- mineru-4.0.3-released · September 18, 2026
- Created
- February 29, 2024
- Last push
- September 19, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 19, 2026GitHub Trending Python today: #12, +62 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/opendatalab/MinerU)Similar projects
-
7.7
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.
-
7.4
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).
-
6.4
Continuum-AI-Corp/OrcaBonsai-27B-Uncensored
A tool for runtime refusal ablation in the compressed Ternary Bonsai 2 27B LLM: it projects the residual stream to remove the refusal direction without modifying or re-quantizing weights. Runs on Apple Silicon via MLX.
-
6.1
jaredpalmer/kev
kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.
-
6.0
githubnext/localjev
A local TypeScript/Bun HTTP service implementing a Jev-compatible POST /v1/systemone API on top of an OpenAI-compatible Chat Completions endpoint (DiffusionGemma via oMLX). It acts as a bridge for typed decisions…
-
6.0
higgsfield-ai/higgsfield
Fault-tolerant GPU orchestration and ML framework for distributed training of models with billions to trillions of parameters, including LLMs. Manages node access, experiment queueing, and GitHub Actions integration.