Memory · Retrieval
Hierarchical / Paging (core vs archival)
Tiered memory, in-context core vs external archival, with data moved between tiers on demand.
Verified against arxiv.org
How it works
Tiered memory, in-context core vs external archival, with data moved between tiers on demand.
At a glance
StageRetrieval
PhaseBoth
Used byMemGPT · Letta (core / archival memory tiers)
Trade-off
Paging and tier-eviction policy add complexity and can evict still-needed data.
Basis
Verified against
https://arxiv.org/abs/2310.08560 The corpus does not rewrite vendor documentation. Where copy is quoted verbatim it is marked as such and attributed to its source.