Summary
A PDF becomes text an agent can actually work with.
The conversion keeps the document's structure instead of flattening it, and the images come out as separate files — which is the difference between a Markdown file you can edit and a wall of extracted characters.
What it is
A PDF-to-Markdown converter built on Mistral AI's OCR. It takes a local file or a remote URL, and writes the converted Markdown and the extracted images into a directory you choose.
What you get
- Local PDF files converted to Markdown, in batches rather than one at a time
- Remote PDFs converted from their URL, without downloading them first
- Document structure preserved — headings, paragraphs and lists come through as Markdown rather than as flat text
- Images extracted from the PDF and saved alongside the output
- The output directory set on the command line, so converted files land where the rest of your work is
Requirements
Python 3.10 or newer with uv, and a Mistral AI API key — supplied in a .env file or in the client config. Documents are sent to Mistral for recognition, and the converted files are written to the output directory, which defaults to ./downloads.