Tiered Memory

memory pattern · maturity: emerging · risk: low

Memory split by access cost: a small always-loaded hot tier (digest, index), a warm tier loaded on relevance (fact bodies), and a cold tier queried explicitly (archives, logs).

When to use

Keeping the per-session context tax flat while total memory grows without bound.

Specification

Memory typesemantic
Storagelayered: file index + fact files + archival store
Retrievalhot always, warm on relevance, cold on explicit query
Update methodwrites land warm; promotion and demotion by usage and age
Decay / staleness handlingDemotion is graceful decay: unused facts sink toward cold instead of being deleted, preserving retrievability without paying context cost.
Risk level / maturitylow / emerging

Privacy and safety

Per-tier access rules; cold archives especially accumulate everything and deserve their own controls.

Failure modes

  • Promotion logic that never demotes, inflating the hot tier
  • Cold tier becoming a write-only graveyard
  • Tier boundaries invisible to the agent, causing missed recalls

Assessment

What indexed fact files grow into when they succeed. The design rule: the hot tier is a budget, not a category, and everything fights for its place there.

Evaluation method: Hot-tier size trend (must stay flat) and cold-tier hit rate on explicit queries.

Go deeper