OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Mineru Skill

Mineru Skill is a Python command-line tool and agent skill that submits PDFs, Office files and images to MinerU’s cloud API and returns parsed Markdown, including OCR, tables and LaTeX content.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mineru Skill — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a workflow needs command-line or agent-accessible document parsing through MinerU, particularly when Markdown output and batch handling are useful.

Who it is for

  • Developers building document-ingestion steps for AI-agent workflows.
  • Users of Claude Code or Cursor who want parsed document text delivered in an agent-friendly format.
  • People preparing source documents for separate knowledge or content tools.

Documented uses

  • Convert supported documents into Markdown for terminal or agent use.
  • Extract text, tables and formula content from documents through MinerU’s parsing service.
  • Process documents in batches using the CLI’s documented batch options.
Before you choose

Requirements & limits

The README documents a token-free Agent API path for its PDF example. Setting MINERU_TOKEN routes requests to the Standard API. The repository is MIT-licensed.

  • The tool is a convenience layer over MinerU’s cloud API, not an independent parsing engine.
  • The documented token-free example handles a PDF URL; the README associates a token with the Standard API’s larger-file, batch and additional-export capabilities.
  • The project describes a standard-library-only core, but parsing remains cloud-based.
  • Markdown output can feed another knowledge system, but the tool is not described as providing RAG-native chunking or indexing.
  • The repository identifies Claude Code and Cursor as supported agent ecosystems.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Convert a public PDF to terminal Markdown

Send a PDF URL through the Agent API and stream its Markdown output to the terminal.

Before you start

  • Python 3.8+; the README also provides a uv invocation.
  • A PDF URL, such as the public demo URL in the documented command.
  • No API token is needed for the documented Agent API example.

Steps

  1. Run the command below.

    Documented command
    python3 scripts/mineru.py https://cdn-mineru.openxlab.org.cn/demo/example.pdf --stdout

  2. Alternatively, run the command below.

    Documented command
    uv run scripts/mineru.py https://cdn-mineru.openxlab.org.cn/demo/example.pdf --stdout

Expected outcome

The Agent API parses the PDF and streams Markdown to the terminal.

Guide limitations

  • This example covers a PDF URL and terminal output; it does not document local-file execution here.
  • Parsing uses MinerU’s cloud API, not an offline engine.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
Nebutra/MinerU-Skill · Official homepage title · retained in its source language
How we review sourcesSuggest a correction