Show HN: Eulix – Code navigation for large codebases

Developer Nurysso released Eulix, an open-source, locally run code navigation tool that parses repositories into symbols and call graphs and combines that structural data with keyword and semantic retrieval. Nurysso tested Eulix on OpenStack, roughly 6.9 million lines of code across 29,000 files, where a query about Nova's PCI passthrough scheduling returned relevant filters, helpers and call paths in well under a second once indexed. Nurysso said Eulix can answer some queries directly from structured codebase data without an LLM and may handle codebases of 30 million or more lines, though that scale has not been tested due to GPU limits for embedding parser output.

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 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 Comments: 0