Why I'm making a PDF viewer

Users of LLMs quickly learn that while these models excel at in-depth learning practices, traditional methods offer unparalleled breadth.

This is why I still turn to textbooks, whitepapers, and technical documents for my structured learning. These often come in the form of PDFs, or a format that can easily be converted into a PDF file.

As a result, I spend a lot of time reading PDFs, whether in Chrome's PDF viewer or the built-in macOS Preview app. I've always felt that the UX in both of these applications wasn't very user-friendly.

I wanted to create a PDF viewer that combined the elements of modern apps with good UX, along with great performance, integrations, and features that users want. Below are some things that I wish were easier when working with PDFs, that I don't really have a good solution for

• Splitting PDFs fast
• Automatically splitting PDFs semantically (using chapter #s, sections, etc)
• Combining PDFs
• Switching between multiple PDFs quickly
• Switching between sections, pages, bookmarks, quickly
• Converting PDF's into context dumps for LLMs
• Really good search filters
• Good organization features
• actually useful LLM features—and not just slop

I'm going to be documenting my progress on this webpage, as well as outlining a roadmap of features I want to add in the future.