I didn't publish the server because it's a vibe coded mess, but if you point your Opus 5.5 at the zip and ask for YouTube-like site it will be basically instant. This part was like 3 min.
EDIT: one caveat is that i couldn't distribute the YouTube data so you'd have to create a (free) API key for that part. Luckily it's only ~1 min of hassle.
I didn't publish the server because it's a vibe coded mess, but if you point your Opus 5.5 at the zip and ask for YouTube-like site it will be basically instant. This part was like 3 min.
EDIT: one caveat is that i couldn't distribute the YouTube data so you'd have to create a (free) API key for that part. Luckily it's only ~1 min of hassle.
I have found out that first round of data scrape/ingestion is pretty easy.
The "black box" (for me) represents the next update. How can I avoid having to download all the data again and just use the new additions?
Do you have a plan for updates?
Well, some portion of it was just served to you over HTTP.
It's very likely that your agents can just build the rest, if the backend source isn't provided.
I think the core data is available here: https://hackertube.org/data