Conducting deep web searches and gathering sources is one of the main things I’ve been using LLMs for. How far away are we from being able to self-host something like Claude’s web search capabilities? Or even just a service where I’d pay with my money instead of my data?
Oh - you can do that right now.
Any decent LLM that can use tools (I still like Qwen3-4B 2507 Instruct) + llama.cpp + OWUI + Tavily API (free key gives you 1000 results a month) or your own SearXNG. Done.
Be aware though that SearXNG is a metacrawler…so if you go crazy with web searching, you will get rate limited up stream.
Else, Kagi.