Per-user data isolation extends beyond sessions to metrics, schedules, evals, knowledge, components, entity memory, and 17 vector databases. Each user's data is scoped to them, and metrics aggregate per user per day, so you can run a multi-tenant product on a single AgentOS with real boundaries between users.
Previously isolation applied mainly to sessions, which left the rest of a deployment pooling data across users. Now the boundary runs through almost everything a user touches. Unowned components and knowledge are treated as shared, readable by everyone and editable by an admin, so enabling isolation doesn't 404 the building blocks you created before it existed.
Learn more in the Per-User Data Isolation docs.
