For context I created a video search engine last year, I shut it down and put the data online. You can read about it here: https://www.bendangelo.me/2024/07/16/failed-attempt-at-creating-a-video-search-engine/

I put that project on hold because of scaling issues, anyway I’m back with an other idea. I’ve been frustrated with how AI slop is ruining the internet and recently it’s been hitting Youitube pretty hard with AI videos. I’m brainstorming a tool for people to selfhost:

Self-hosted crawler: Pick which sites/videos to index (blogs, forums, YT channels, etc.). AI chat interface: Ask questions like, “Show me Rust tutorials from 2023” or “Summarize recent posts about homelab backups.” Optional sharing: Pool indexes with trusted friends/communities.

Why? No Google/YouTube spam—only content you choose. Works offline (archive forums, videos, docs). Local AI (Mistral) or cloud (paid) for smarter searches.

Would this be useful to you? What sites would you crawl? Any killer features I’m missing?

Prototype in progress—just testing interest!

  • 𞋴𝛂𝛋𝛆@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    10 days ago

    Take pipe pipe and index my watch history. Save a copy if whatever I watched, transcribe it and index that information.

    Save a list of recent conversational points based on things I’ve watched that might make interesting or engaging small talk.

    Automatically organize my hobbies looking for patterns too. I don’t. Are about external like I care about organizing what is already getting juggled around.