Standalone vector database with SQL, SPARQL, Cypher + IndexedDB persistence - fully in the browser via WASM
High-performance similarity search with cosine, euclidean, and dot product metrics
Property graph queries with CREATE, MATCH, WHERE, RETURN support
RDF triple store with SELECT queries and pattern matching
Familiar SQL syntax for vector operations with pgvector compatibility
Save and load database state in the browser using IndexedDB - data persists across sessions