← back to the directory
Library / SDK Retrieval & Memory

ScaNN

1Efficient 2vector 3similarity 4search 5from 6Google.

the six Ws · specification

W1 Who

By Google Research.

W2 What

A library for fast approximate nearest-neighbor search at scale.

W3 Where

A Python/C++ library in your service.

W4 When

When you need high-recall ANN search.

W5 Why

State-of-the-art speed and accuracy tradeoffs.

W6 With

Python and TensorFlow-compatible tooling.

W7 Watch

Apache-2.0, from Google Research; runs locally, no credentials.

ANNGoogleVector-search

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.