MinerU
MinerU is a high-quality, open-source tool that enables one-stop data extraction, specifically designed to convert PDF documents into Markdown and JSON formats.
There are 3 open-source alternatives to pandoc in this directory. The most popular is MinerU with 40.9k GitHub stars, followed by Marker(22.8k stars). All are open source, free to use, and many can be self-hosted.
| # | Tool | Stars | Language | License |
|---|---|---|---|---|
| 1 | MinerU MinerU is a high-quality, open-source tool that enables one-stop data extraction, specifically designed to convert PDF documents into Markdown and JSON formats. | 40.9k | Python | GNU Affero General Public License v3.0 |
| 2 | Marker Convert PDF files to Markdown and JSON formats quickly and with high accuracy, suitable for diverse data extraction needs. | 22.8k | Python | GNU General Public License v3.0 |
| 3 | VERT The next-generation file converter that is open source, fully local, and free forever. It supports multiple file formats and ensures privacy by running completely offline. | 5.2k | Svelte | GNU Affero General Public License v3.0 |
MinerU is a high-quality, open-source tool that enables one-stop data extraction, specifically designed to convert PDF documents into Markdown and JSON formats.
Convert PDF files to Markdown and JSON formats quickly and with high accuracy, suitable for diverse data extraction needs.
The next-generation file converter that is open source, fully local, and free forever. It supports multiple file formats and ensures privacy by running completely offline.
The top three are MinerU(40.9k stars), Marker(22.8k stars), VERT(5.2k stars). All are open source and free to use.
Yes. Every tool listed here is open source and free to use in your own projects. Many can be self-hosted on your own infrastructure, which means no subscription fees and full control over your data.
Many of the alternatives listed are self-hostable. Each tool's page lists hosting details, system requirements, and licensing terms.
Get notified about new tools and updates to existing ones.