Corpus Agentis
The field book to agent ecosystems
The field book to agent ecosystems
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.