CLI tool for detecting non-exact code duplication with embedding models
Details
- External ID
- 48762038
- Source
- HN
- Company
- —
- Product
- CLI tool for detecting non-exact code duplication with embedding models
- Website domain
- github.com
- Launched
- July 2, 2026
- Cohort
- —
- Upvotes
- 91
- Upvotes percentile
- 0.9026284348864994
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Enrichment
- Theme
- developer tools and programming utilities
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- detect code duplication with embeddings
- Manually corrected
- False
Could you build this?
Yes Splitting code into chunks (e.g., using tree-sitter functions), generating embeddings via an API or local model, and computing cosine similarity or vector search is easily vibe-coded.
Discussion
20 comments analyzed.
Competitors mentioned: jscpd (copy/paste detector), SemHash (deduplication library)
Concerns raised: LLM hallucination with embedding-based detection, O(n²) brute-force similarity search doesn't scale for large projects, High memory usage for large repos (4.8GB+ for Kubernetes), Performance bottleneck: ~130s+ on large projects like Kubernetes, False positives in similarity detection need manual cleanup
Feature requests: Generate and run test units to verify if similar code produces same results, More granular code chunking below function level, Local model support for embeddings, Support for additional languages (Elixir, PHP mentioned as recent additions)
Competitors
Other products that read as similar to this one — 1317 launches clear the similarity bar, closest 8 shown.
Attention rank: #128 of 1318 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 244 days after the earliest competitor.
- Onboard-CLI, a LLM powered and AST-based tool to visualize codebase · hn · 2026-07-08 · 24 upvotes · similarity 0.63
- Jeff · hn · 2026-09-18 · 27 upvotes · similarity 0.58
- Arbor · hn · 2026-03-05 · 5 upvotes · similarity 0.57
- perch · github · 2026-09-16 · 164 upvotes · similarity 0.56
- Modivue · github · 2026-09-13 · 17 upvotes · similarity 0.55
- Vho · hn · 2026-01-05 · 7 upvotes · similarity 0.55
- ZedLite · github · 2026-09-23 · 223 upvotes · similarity 0.55
- repro-lens · github · 2026-09-13 · 9 upvotes · similarity 0.54
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.