Memory Types & Concepts

Rekall models AI memory across seven distinct types, each optimized for different kinds of knowledge. Understanding these types is key to building agents that remember, learn, and improve over time.

Getting started?

If you are new to Rekall, start with Episodic Memory and Semantic Memory. These two types cover the most common agent memory needs.

Memory Types

Comparison Table

TypeStorageTTL / LifecycleUse Case
EpisodicPostgreSQL + QdrantDecays over timeConversation history, events, meeting notes
SemanticNeo4j + GraphitiPersistentKnowledge graphs, entity relationships, facts
ProceduralPostgreSQLPersistentWorkflows, checklists, learned processes
Long-TermPostgreSQL + QdrantImportance-based decayConsolidated knowledge, patterns, insights
Short-TermRedisTTL (default 3h)Session context, working state, temp data
ExecutionPostgreSQLTask lifetimeAgent task state, checkpoints, pause/resume
PreferencesPostgreSQLPersistentUser preferences, style patterns, choices

Memory Contexts

Memories exist within contexts that control isolation and sharing. Rekall supports three context types:

PersonalPer-user memories, private to the individual. Default context.
HiveShared team memories, accessible to all members of an organization.
AgentPer-agent memories, including husk identity and agent-specific knowledge.
Learn more about memory contexts →

Decay & Consolidation

Rekall models memory strength using an Ebbinghaus-inspired decay curve. Memories naturally fade over time unless reinforced through access. The consolidation process periodically extracts patterns from episodic memories into long-term storage, preserving key insights while allowing details to decay.

Learn about decay and consolidation →

Relationships

Memories do not exist in isolation. Rekall tracks cross-memory connections including semantic relationships between entities, references from episodic memories to entities, and temporal chains of events.

Learn about memory relationships →

Next Steps

Rekall
rekall