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!
While almost everyone here seems to hate AI (maybe for the wrong reason, but who am I to judge) I like to have AI as it is able to provide answers a simple search engine cannot.
What I don’t see is hosting something like this myself. The managing of source and indexing them would take too much of my, my server’s and the web servers to be indexed energy (maybe I am wrong).
There are already good solutions (OpenWebUI with Ollama) that can be tweaked to almost do what you’re describing and the AI models get better every month, so I don’t think a custom AI search engine could keep up with it.