Technologies

What is MinerU built with?

Q: Which repos have a stack like MinerU's?

The ones that share most of its stack: datawhalechina/hello-agents, debpalash/VoiceStudio, and unslothai/unsloth.

MinerU is a Python repo built with FastAPI and uvicorn. It stores its data in SQLite, uses AI through onnxruntime, ModelScope, ONNX, tokenizers, and OpenAI, makes its content with mineru, pillow, beautifulsoup4, and pypdfium2, validates its data with Pydantic, deploys with loguru, and uses aiosqlite and Hugging Face. It has 158,109 written lines, with 236 test files.

Read on November 4, 2026, at commit 8cd0842. Read it as markdown

Frontend

Interface

Rich7 files
Gradio4 files

MinerU375 files

Backend

The base

FastAPI10 files

Data

aiosqlite
SQLite3 files · mineru/doclib/core/db.py, line 11

AI

onnxruntime7 files
ModelScope1 file
ONNX1 file
tokenizers1 file

Services

Hugging Face1 file · mineru/model/download.py, line 13
OpenAI1 file · mineru/backend/postprocess/llm_client.py, line 13

Support

The base

uvicorn4 files

Content

mineru203 files
pillow23 files
beautifulsoup44 files
pypdfium21 file

Validation

Pydantic18 files

Deploy

loguru41 files

Tools

Typer29 files
packaging5 files
click4 files
typing-extensions1 file
watchfiles1 file

Other

python-multipart
NumPy46 files
httpx14 files
tqdm10 files
filelock8 files
pyyaml7 files
shapely2 files
ftfy1 file
jieba1 file
json-repair1 file
pyclipper1 file
requests1 file

Other repos with a similar stack

Ordered by how much of its stack they share with MinerU, then by stars.

datawhalechinahello-agents
86k
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
14 of 35 in commonCompare →
debpalashVoiceStudio
100.7k
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
10 of 35 in commonCompare →
unslothaiunsloth
79.1k
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
9 of 35 in commonCompare →
Significant-GravitasAutoGPT
187.9k
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
8 of 35 in commonCompare →
unclecodecrawl4ai
86.9k
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.
8 of 35 in commonCompare →
open-webuiopen-webui
157.7k
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
7 of 35 in common · SvelteCompare →