Original Summary

Hey I&#x27;ve been working on Eulix, a tool for navigating large codebases.<p>It parses a repository into symbols, call graphs and other structural information, then combines that with keyword and semantic retrieval to find relevant code.<p>I tested it on OpenStack (~6.9M LOC &#x2F; 29k files). One query about Nova&#x27;s PCI passthrough scheduling pulled back the relevant filters, helpers and related call paths in well under a second once indexed.<p>Some queries don&#x27;t need an LLM at all, since Eulix can answer directly from the structured codebase data.<p>It&#x27;s open source and runs locally:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;Nurysso&#x2F;eulix" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Nurysso&#x2F;eulix</a><p>I&#x27;d especially like feedback from people who&#x27;ve worked on code search, static analysis, or large monorepos.<p>on a side note it may be able to handle 30M+ loc codebase too, I haven&#x27;t been able to test such huge repos cause I don&#x27;t have a good enough gpu to embed parsers output! :)

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/15 23:41:18