Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Eulix

Code navigation for large codebases

Details

External ID
49714268
Source
HN
Company
—
Product
—
Website domain
—
Launched
Sept. 15, 2026
Cohort
—
Upvotes
5
Upvotes percentile
0.12998405103668262
Tags
—
Fetched at
Sept. 19, 2026, 5:01 p.m.
Updated at
Sept. 19, 2026, 5:01 p.m.

Description

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/eulixI'd especially like feedback from people who've worked on code search, static analysis, or large monorepos.on a side note it may be able to handle 30M+ loc codebase too, I haven't been able to test such huge repos cause I don't have a good enough gpu to embed parsers output! :)

Enrichment

Theme
Claude integrations and coding agents
Vertical
Horizontal
Function
Dev tools
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
code navigation tool for large codebases
Manually corrected
False

Could you build this?

Partial Basic AST extraction and semantic search are standard, but scaling symbol extraction and call-graph resolution across multi-million LOC codebases (like OpenStack) with interactive low latency requires specialized static analysis pipelines.

What it would actually take: Requires tree-sitter or LSP-based semantic indexing, a graph database or custom in-memory graph index for cross-file symbol references and call hierarchies, combined with an embedding model and vector database (e.g., Qdrant/LanceDB) and BM25 search. The hard part is incremental graph construction and disambiguation across thousands of Python files without crashing or running out of memory.

Discussion

No comments on this launch.

Competitors

Other products that read as similar to this one — 115 launches clear the similarity bar, closest 8 shown.

Attention rank: #90 of 116 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 314 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a dev tools tool for Sales yet.