A library to perform semantic vector search, over millions of vectors in milliseconds, and can even visualize the tokens or embeddings too; runs entirely client side in the web browser (custom Vector DB layer written on top of IndexDB) and currently supports Google's EmbeddingGemma (highest quality but 300Mb), or all-Mini-L6-v2 (fastest and only 30mb) embedding models via Web AI libraries with WebGPU acceleration for speed.