Nicheloom

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

Sqry

semantic code search using AST and call graphs

Details

External ID
47282106
Source
HN
Company
—
Product
Sqry
Website domain
sqry.dev
Launched
March 6, 2026
Cohort
—
Upvotes
5
Upvotes percentile
0.1070110701107011
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Description

I built sqry, a local code search tool that works at the semantic level rather than the text level.The motivation: ripgrep is great for finding strings, but it can't tell you "who calls this function", "what does this function call", or "find all public async functions that return Result". Those questions require understanding code structure, not just matching patterns.sqry parses your code into an AST using tree-sitter, builds a unified call/ import/dependency graph, and lets you query it: sqry query "callers:authenticate" sqry query "kind:function AND visibility:public AND lang:rust" sqry graph trace-path main handle_request sqry cycles sqry ask "find all error handling functions" The `sqry ask` command translates natural language into sqry query syntax locally, using a compact 22M-parameter model with no network calls.Some things that might be interesting to HN:- 35 language plugins via tree-sitter (C, Rust, Go, Python, TypeScript, Java, SQL, Terraform, and more) - Cross-language edge detection: FFI linking (Rust↔C/C++), HTTP route matching (JS/TS↔Python/Java/Go) - 33-tool MCP server so AI assistants get exact call graph data instead of relying on embedding similarity - Arena-based graph with CSR storage; indexed queries run ~4ms warm - Cycle detection, dead code analysis, semantic diff between git refsIt's MIT-licensed and builds from source with Rust 1.90+. Fair warning: full build takes ~20 GB disk because 35 tree-sitter grammars compile from source.Repo: https://github.com/verivusai-labs/sqry Docs: https://sqry.devHappy to answer questions about the architecture, the NL translation approach, or the cross-language detection.

Enrichment

Theme
browser automation and scraping for AI
Vertical
Horizontal
Function
Search & retrieval
Audience
Developer
AI stance
Not AI
Project type
Commercial product
Normalized one-liner
semantic code search
Manually corrected
False

Could you build this?

Partial Building a basic AST query wrapper is accessible, but building a production-grade semantic code search engine supporting 37 languages with complete call graphs and fast indexing requires serious compiler-frontend engineering.

What it would actually take: The architecture uses Rust with Tree-sitter parsers across dozens of languages, constructing persistent ASTs, symbol tables, and cross-file call graphs into an indexed database. The hard parts are cross-file symbol resolution across heterogeneous language semantics (imports, scoping, dynamic dispatch) and sub-second query performance over massive codebases. Requires deep expertise in compiler theory, program analysis, and high-performance graph indexing.

Discussion

1 comment analyzed.

Competitors mentioned: Neo4j

Competitors

Other products that read as similar to this one — 72 launches clear the similarity bar, closest 8 shown.

Attention rank: #65 of 73 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 127 days after the earliest competitor.

Other launches for this product