Documents & OCR
13Convert between formats, manipulate PDFs, pull text out of images and scans, and turn documents into clean markdown an LLM can read.
Conversion
- Pandocuniversal document converter (Markdown, HTML, DOCX, PDF, LaTeX, ODT, and more); the go-to for any format-to-format job.
- LibreOffice
libreoffice --headless --convert-toscripts Office-format conversion (DOCX/XLSX/PPTX to PDF, etc.) without a GUI. - Typstmodern typesetting engine with a fast CLI; generate PDFs from lightweight markup, a saner LaTeX.
- mdcatrender Markdown to the terminal (cat for Markdown); pipe-friendly display.