Overview

The preference layer your AI product is missing.

Galya sits underneath your product, indexing what your content means, learning what your users want, and giving your AI the context to act on both.

Three stacked product layers in an exploded isometric view: Taste Graph, Customer Intelligence, and Content Intelligence.
How it fits together
1Index
2Capture
3Query

Index your data, catalog, or inventory. Capture how users engage with it. Query the Taste Graph for search, reranking, and agent context.

All in real time, and at inference.

The engine

Taste Graph

A living map of who your users are, queried at inference.

Put it to work

Customer Intelligence

Segments defined by shared aesthetic sensibility and content affinity, not demographics.

Explore →

Content Intelligence

Every asset encoded for meaning across aesthetic, mood, tone, and intent.

Explore →
Developer layer

@galya/sdk

Capture engagement signals from your UI in minutes.

@galya/agents

Search, rerank, ask, and explain, relative to any user or entity.

Agent Tools

Every method as a galya_* tool for function-calling models.

00010002000300040005000600070008000900100011001200130014cluster Acluster Bcluster Ccluster D/similar/cluster/score/recommend/graph

Ready to give your AI taste?

Book a demo and see your first Taste Graph composed live, from cold-start to a callable preference layer.