LisaOS Docs
Memory

Three-Layer Memory Stack

Operational, persistent, and dialectic memory — three stores with different latencies and lifecycles.

LISA's memory is a stack of three layers, each answering a different question.

LayerStoreLatencyPurposeLifecycle
OperationalPsychic Cache<100ms"What was decided?" — directives, decisions, intel, state changesTTL-based expiry + manual GC
PersistentGateway memory (with embeddings)~200msLong-term knowledge, preferences, summariesPermanent until deleted
DialecticHoncho~500msAutonomous user/AI modellingSession-scoped, auto-summarised

Memory taxonomy

Four native types run a three-tier priority system:

TierTypePriorityEviction
1Procedural (user / feedback)Always loadedNever evicted
2Evergreen projectLoaded by relevanceLeast-relevant first
3Session semanticLoaded newest-firstOldest-first
3Session episodicOn-demand onlyFirst to evict

Tier 1 memories shape every interaction and are loaded unconditionally. Tier 2 and Tier 3 are pulled by relevance at context assembly time.

Memory flow

Writes fan out to the layer that matches the fact's lifetime; reads converge through a single context-assembly step that weights every source before it reaches the model.

Every assembly is paired with a feedback call, closing the loop that tunes each source's weight over time — see context feedback.

The layers in detail

On this page