← All updates Databricks Update One-Pager Light version
databricks Platform · Updated Sep 16, 2026

Managed agent memory and sessions are in Beta

Managed agent memory and managed agent sessions are in Beta.

What it does

Managed agent memory and managed agent sessions are in Beta. Databricks now provides two fully managed, Lakebase backed stores for agent state, both usable from agents built on any framework: Managed agent memory gives agents durable, long term memory that persists across conversations, with semantic search. Managed agent sessions store durable conversation history that an agent reads at the start of a turn and appends to as it runs.

Why it matters

Reduces operational overhead and unlocks new capabilities for data teams on Databricks.

Key capabilities
actorid (required): who the session
actorid (required): who the session belongs to, such as an end user or another agent. It groups all of one subject's sessions so…
sessionid (optional): a caller-chosen ID
sessionid (optional): a caller-chosen ID for the interaction. The service generates one when you omit it.
parentsessionid (optional): links a session
parentsessionid (optional): links a session to the one it was forked from, to represent branched conversations. A session item…
Architecture
Databricks Platform → Platform
In short

Managed agent memory and managed agent sessions are in Beta. Databricks now provides two fully managed, Lakebase backed stores for agent state, both usable from agents built on any framework: Managed agent memory gives agents durable, long term memory that…

Read the full documentation ↗
Key takeaway
Managed agent memory and managed agent sessions are in Beta.
2026-09-16-managed-agent-memory-and-sessions-are-in-beta Generated by the Databricks Updates Agent · browse all updates