As a fellow tab/bookmark (and sessionstore.json and other extension-based export) hoarder, I wonder if our lives could be helped by LLM curation and organization of this mess. Like vague queries against this backlog, like is there anything related to XYZ topic or aspect in the pile? What's the overall composition of this heap of links? How does this composition change over time? Can we plot a 2D scatterplot of all the links with proximity based on semantic/topical similarity?

Or maybe we just need to learn how to prioritize better? Or do some kind of stagewise workflow where the superficial ingestion/collection is followed by multiple steps of culling the less relevant stuff (but still without real deletion, just in case for later). Or perhaps we could now write a sentence of why we think the link may be relevant and what future event or future state of some project or development might make this link gain in relevance again? And then again we could declare that this has happened and what are now the links that are relevant?

I could see some LLM product in this space, but I think this market is fairly niche.

I'd like a fixed-sized queue of 10 links. Adding one more kicks the oldest and it can be only read as strict first-in-first-out.