Dicklesworthstone/frankensearch

Two-tier hybrid search for Rust: sub-millisecond initial results via potion-128M, quality-refined rankings in 150ms via MiniLM-L6-v2. Combines lexical (Tantivy BM25) and semantic (vector cosine) search with Reciprocal Rank Fusion. Progressive iterator API, f16 SIMD vector index, feature-gated compilation.

45
/ 100
Emerging

This tool helps technical professionals quickly find information within their local files, like project documentation or codebases. It takes a natural language query or keywords as input and provides a fast initial set of relevant results, followed by a more refined and accurate ranking shortly after. Software developers, operations engineers, or researchers working with large local text corpora would find this useful.

Use this if you need to perform rapid, high-quality searches across your personal or project-specific files, blending keyword precision with semantic understanding.

Not ideal if you need to search public web content, manage a global enterprise search engine, or if your primary need is strictly exact keyword matching without semantic nuance.

local-search developer-tools documentation-retrieval codebase-navigation knowledge-discovery
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 17 / 25

How are scores calculated?

Stars

41

Forks

9

Language

Rust

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Dicklesworthstone/frankensearch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.