How Memory Works
Memory lets agents retain information across conversations. When an agent learns something about you or its own context, it can store that as a fact. These facts persist and are available in future conversations.
Memory scopes
Section titled “Memory scopes”There are several types of memory, each serving a different purpose:
User memory
Section titled “User memory”Facts about you that are shared across all agents. If you tell one agent your name or preferences, any agent can access that information.
Stored with the remember_user_fact tool.
Agent memory
Section titled “Agent memory”Facts specific to a single agent. These are private to the agent that created them and not visible to other agents.
Stored with the remember_agent_fact tool.
Agent identity
Section titled “Agent identity”Persistent personality information for an agent. Its name, traits, communication style. Updated through the update_identity tool.
Space context
Section titled “Space context”Auto-generated summaries of conversations within a space. The platform creates these automatically through compaction. Agents don’t manage them directly.
How memory is used
Section titled “How memory is used”When an agent starts a conversation, the platform loads relevant memory into the context:
- User facts (shared across agents)
- Agent-specific facts
- Agent identity
- Space context (if the chat is linked to a space)
This happens automatically. You don’t need to tell the agent to “remember” to check its memory.
Storing facts
Section titled “Storing facts”Agents store facts using the remember_user_fact and remember_agent_fact tools. They can also update existing facts when information changes by setting overrides: true.
The platform gives agents guidelines for memory management:
- Read existing memory before storing new facts to avoid duplicates
- Use overrides when correcting or updating existing information
- Keep facts concise and specific
- For large data, save to a workspace file and reference it in memory
Memory compaction
Section titled “Memory compaction”Over time, memory accumulates. The platform runs periodic compaction to keep it manageable:
- Insight compaction (default: every 2 hours). Merges, deduplicates, and cleans up memory facts
- Space compaction (default: every hour). Summarizes conversation history within spaces
Compaction runs automatically in the background. You can tune the intervals with FRONA_SCHEDULER_INSIGHT_COMPACTION_SECS and FRONA_SCHEDULER_SPACE_COMPACTION_SECS.
See Insights for more on how compaction works.