mensonones/expo-vector-search

High-performance on-device vector search engine for Expo & React Native. Powered by C++ JSI and USearch (HNSW) for sub-millisecond similarity matching.

29
/ 100
Experimental

This project helps app developers add intelligent search features to their mobile applications without needing a server. It takes data like product images or text descriptions, converts them into 'vector embeddings,' and then allows for ultra-fast, on-device searching for similar items. App developers can use this to create features such as visual product search, automated customer support message routing, or on-device content moderation.

Use this if you are a mobile app developer looking to build fast, privacy-focused semantic search or machine learning features directly into your Expo or React Native applications.

Not ideal if your application requires traditional exact-match database queries or if you prefer server-side processing for all search functionality.

mobile-app-development e-commerce customer-support content-moderation on-device-AI
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 11 / 25
Community 0 / 25

How are scores calculated?

Stars

53

Forks

Language

C

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/mensonones/expo-vector-search"

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