MeMemo

A powerful, lightweight in-browser vector database that wraps IndexedDB and Transformers.js over WebAssembly, enabling semantic search and AI memory entirely in the browser without server requirements.

A portable WebAssembly vector similarity search engine written in Rust with a tiny footprint (75KB gzipped). Designed for edge deployment, browsers, and IoT devices with support for k-d tree indexing and optimized for modern web applications.

Semantic caching solution for LLM applications that reduces API calls and costs by recognizing semantically similar queries. Achieves up to 73% cost reduction in conversational workloads with sub-millisecond cache retrieval through vector similarity search.

Node.js bindings for HNSWlib implementing approximate nearest-neighbor search. Provides fast HNSW-based vector similarity search for JavaScript/TypeScript applications with file persistence support.

LangChain is an open-source framework that integrates with various vector databases, including Pinecone, Weaviate, and Chroma, to facilitate retrieval-augmented generation (RAG) and advanced AI workflows.

RETA-LLM is a toolkit designed for retrieval-augmented large language models. It is directly relevant to vector databases as it involves retrieval-based methods that typically leverage vector search and vector databases to enhance language model capabilities through external knowledge retrieval.