Built for researchers, students, writers, and professionals who manage many PDFs.
PDF annotations — highlights, comments, and sticky notes — contain some of the most valuable insights from your reading. Yet extracting them from a PDF has historically required expensive desktop software or cloud-based services that upload your private documents to remote servers. We set out to change that.
PDFs are parsed in your browser with WebAssembly. After the page opens, you can disconnect from the internet and the tool will continue to work.
As users of Obsidian and Notion, we wanted to close the gap between reading PDFs and turning their annotations into structured notes.
The extraction engine runs a compiled PDF parser in the browser through WebAssembly, without a server round-trip for the document. Supported annotation types and metadata depend on the source PDF.
Open an annotated PDF and see the local extraction result.
Try the Tool