lancedb/lancedb

Health v2 · maintenance only

Adoption not part of the score

11284 stars · 1027 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

LanceDB is an open-source embedded vector database and multimodal AI lakehouse built on the Lance columnar format, written in Rust with Python, TypeScript, and Rust SDKs. It supports fast vector similarity search, full-text search, and SQL over billions of vectors and multimodal data without managing separate server infrastructure.

Use cases

• store and search embeddings for a RAG application
• build semantic search over documents, images, or videos
• run a local vector database without a separate server
• find similar images by embedding similarity
• build a recommendation system with nearest-neighbor search
• curate and version training data for ML pipelines
• combine vector search with SQL filtering and full-text search

When to choose

• you want an embedded, serverless vector store that runs locally or on object storage
• you need multimodal data (text, images, video, point clouds) alongside vectors in one table
• you want zero-copy versioning of datasets without extra infrastructure
• you need fast ANN search at scale with GPU index building

When to avoid

• you need a fully managed multi-tenant database service with built-in access control (consider LanceDB Enterprise or a hosted DB)
• your workload is purely relational OLTP with no vector or search needs
• you require rich secondary-index transactional semantics of a traditional RDBMS

Facets

library · maturity active

vector-database search-engine database rag databases machine-learning artificial-intelligence data-science rust python cross-platform cli embedded-database similarity-search multimodal-ai lance-format ann-search full-text-search serverless search retrieval-augmented-generation nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lancedb/lancedb")