MinerU83.2k

opendatalab/MinerU

Open sourceFreeProductivity & NotesSelf-hosted

What is MinerU?

Converts PDFs and Office documents into LLM ready Markdown or JSON. It has 83,191 stars on GitHub and ranks #3 in Productivity & Notes. You can host it on your own server and keep your data.

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

Platforms

WebDockerCommand line

More Productivity & Notes

MarkItDown194k

Tool that converts Office documents, PDFs and other files into Markdown text.

Command line

Stirling PDF95.8k

Tool for merging, splitting, converting and editing PDF files on any device.

Self-hostedWindowsMacLinuxWebDocker

AppFlowy78.2k

Open source Notion alternative with AI for notes, wikis and projects.

Self-hostedWindowsMacLinuxAndroidiPhone

Tesseract77.4k

Command line OCR engine that extracts text from images and scanned documents.

WindowsMacLinuxCommand line

AFFiNE74.2k

Workspace that merges notes, docs and whiteboards, a self-hostable Notion and Miro alternative.

Self-hostedWindowsMacLinuxWebDocker

Memos64.3k

Lightweight open source note-taking app you host yourself, with Markdown support for everyday thoughts.

Self-hostedWebDocker

MarkText63.6k

Simple and elegant Markdown editor with real-time preview for Windows, macOS and Linux.

WindowsMacLinux

Plane62k

Open source project management tool, an alternative to Jira and Linear.

Self-hostedWebDocker