Hey I've been working on Eulix, a tool for navigating large codebases.
It parses a repository into symbols, call graphs and other structural information, then combines that with keyword and semantic retrieval to find relevant code.
I tested it on OpenStack (~6.9M LOC / 29k files). One query about Nova's PCI passthrough scheduling pulled back the relevant filters, helpers and related call paths in well under a second once indexed.
Some queries don't need an LLM at all, since Eulix can answer directly from the structured codebase data.
It's open source and runs locally:
https://github.com/Nurysso/eulix I'd especially like feedback from people who've worked on code search, static analysis, or large monorepos.
on a side note it can possibly handle 30M+ loc codebase too, I haven't been able to test such huge repos cause I dont have a good enough gpu to embed parsers output :)
Comments URL: [https://news.ycombinator.com/item?id=49714268](https://news.ycombinator.com/item?id=49714268)
Points: 2