rryam/VecturaKit

Swift-based vector database for on-device RAG using MLTensor and MLX Embedders

51
/ 100
Established

Supports multiple embedding models (Model2Vec, NomicBERT, ModernBERT, RoBERTa) with pluggable providers including Apple's NaturalLanguage framework for zero-dependency contextual embeddings and optional MLX GPU acceleration. Features hybrid BM25 + vector search, batch parallel indexing, and configurable memory strategies (automatic, full-memory, or indexed modes) for datasets from thousands to millions of documents. Includes a CLI tool (`vectura-cli`) for testing and spans iOS 17+, macOS 14+, and visionOS platforms.

263 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

263

Forks

25

Language

Swift

License

MIT

Last pushed

Mar 05, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/rryam/VecturaKit"

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