Agent Memory
The persistence layer through which an agent carries state across invocations — prior decisions, retrieved documents, learned preferences — distinct from both the model weights and the context window.
Why it matters
Memory is the component that governance frameworks have not noticed. Weights are versioned and reviewed; memory accumulates silently and changes behavior with no model change at all. Two deployments of an identical model with different memory states are different systems, and no current model risk process would catch it.
What it is not
These are routinely confused with Agent Memory. The distinctions are not pedantic — each one has consequences for how a system is governed.
Memory is what gets selected INTO the window. The window is the budget; memory is the store.
A retrieval corpus is shared and curated. Memory is per-agent and accrues from the agent's own history.
Relationships
Typed edges into the rest of the ontology. These are what make the canon traversable rather than merely readable.
| Verb | Target | Meaning |
|---|---|---|
dependsOn | Agent memory | The subject cannot function correctly without the object. |
requires | Audit Trail | The subject imposes the object as a precondition. |
addresses | Auditability | The subject speaks to the object as a question or concern. |
Record
| Canonical identifier | QIS-TERM-00010 |
| Status | Canonical industry term |
| Adoption | Emerging |
| Domain · Layer | Context & memory · Intelligence |
| Origin | Convergent usage across agent frameworks from 2024 onward. |
| Semantic aliases | None recorded. |
| First published | 2026-08-02 |
| Last reviewed | 2026-08-02 · 180-day cycle |
Cite the identifier, not the URL. Identifiers are stable; URLs may change. This entry is free to read, quote and index under the dual license. Corrections to [email protected] are published.