LanceDB

Embedded serverless vector database — SQLite-style, multimodal, no server to run.

Install Repository Website Compare

Fit.

Catalog snapshot

Platforms: Linux, Macos, Windows
Operating systems: Linux, macOS, Windows
Ram floor: 1 GB
Gpu: Not needed
Docker: No
Setup: Beginner
Deploy as: Local, Self-hosted
Commercial use: Allowed

Embedded model; scale by pointing many readers at the same object store.

Project.

Fetched Sep 12, 2026¹

License: Apache 2.0
Stars: 11.4k¹
Forks: 1k¹
Open issues: 468¹
Language: Rust¹
Last commit: Sep 12, 2026¹
Tags: embeddedmultimodalrust

About.

LanceDB is an embedded vector store in the SQLite tradition: no server, files on disk, Rust core with Python and TypeScript bindings. Built on the Lance column format for multimodal AI data. Apache-2.0.

embedded engine · multimodal vectors · versioned tables · full-text + vector hybrid

Alternatives.

Nearby.

All Vector databases

TtxtaiAll-in-one Python framework for embeddings, vector search, and RAG workflows.Compare
QQdrantRust vector database with filters, payloads, and a REST API.Compare
WWeaviateVector database with hybrid search and modular vectorizers.Compare
MMilvusCloud-native vector database built for large-scale ANN search.Compare
CChromaDeveloper-friendly embedding database for local RAG prototypes.Compare