Show HN: TabCrunch Analyses and Categorises the Browser Tabs Using LLMs

Hey HN,

Here is a side project that's the result of several months of work of a small team. We wanted to help people (and ourselves!) get through the piles of unread browser tabs and bookmarks that inevitably build up as we read and research. The idea is to have a single place to organise all tabs across devices and browsers. The really valuable part is the deep understanding of the context of all different topics and their summarisations. This allows you to go much faster through the content.

TabCrunch is a browser extension, so you will have to download it to your browser but after that you will be able to test it immediately and for free. I suggest using this code: TECHDEEPDIVEHNAPRIL24 to get 20 analysis of up to 500 links each. Here is a link to the extension: https://tabcrunch.com/install.html

For anyone interested in the technical side of things, here's a short writeup: https://tabcrunch.com/technical-deep-dive.html It turns out that this task is super demanding for today’s LLMs so we describe our methodology as well as a lot of what we have learned along the way. I hope it helps others experimenting with LLMs and I hope you find TabCrunch useful too.

Looking forward to hearing your feedback.