← back to the directory
Library / SDK Retrieval & Memory

LanceDB

1Embedded 2vector 3database 4for 5AI 6apps.

the six Ws · specification

W1 Who

Open-source project from LanceDB.

W2 What

Stores vectors and metadata in a fast columnar format.

W3 Where

Embedded in-process or serverless.

W4 When

When you want a lightweight local vector store.

W5 Why

Multimodal, serverless, and simple to embed.

W6 With

An embedding model and your data.

RustVector-DBEmbedded

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.