DATABASES Signal 244
How Redis brings persistent memory to Snowflake Cortex Agents
↗
Redis Agent Memory is now available on the Snowflake Marketplace, giving Cortex AI agents a persistent memory layer that survives across sessions inside the Snowflake account boundary.
For teams building agents on Snowflake Cortex, the main limitation has been that context vanishes when a session ends, forcing every interaction to start from scratch. This integration closes that gap without introducing external infrastructure or data egress, which matters for enterprises that need context to compound over time while staying within their existing data governance perimeter. Only one feed carried this story, so the claims rest on a single source.
Written by elseif from the cluster below · every claim links back to a sourceThe three things worth knowing
Redis Agent Memory installs from the Snowflake Marketplace and runs on Snowpark Container Services inside the customer's account, with no data leaving the warehouse.
The system exposes four memory types, episodic, semantic, user preference, and procedural, and a hydrate_prompt() function that assembles relevant context before the model responds.
Memory is scoped by user and namespace, allowing isolation across users, applications, tenants, or environments, and the interface is pure SQL.
THE CLUSTER