Skip to main content
Herm carries useful context across sessions without requiring your application to replay every prior turn. Memory is scoped to the organization, agent, and stable subjectId supplied when a session is created.

Memory

The built-in memory tool lets the agent save, replace, and remove durable facts. session_search lets it retrieve relevant context from previous conversations. Both toolsets can be configured through the agent’s tools array.
Reuse the same subjectId for the same person, team, organization, or workspace. Changing it intentionally creates a separate memory and workspace boundary.

Self-learning

After turns, Hermes periodically reviews work to identify durable facts and reusable procedures. Useful procedures can become learned skills in the subject’s persistent workspace and can inform later sessions. Background review is asynchronous and best effort; do not use it as the system of record for data your application must retain. Put mandatory instructions in the agent’s configured skills array instead. Configured skills are versioned agent configuration. Learned skills are scoped to an agent and subject and survive across sessions. Public learned-skill management endpoints are not currently available. See Skills for configured skill behavior and Tools for memory tool controls.
Last modified on July 25, 2026