R3 Updated 2026-06-20
Schema-marked glossary

Agent Memory Glossary

A schema-marked glossary of agent memory terms, including inspectability, supersession, provable forgetting, retrieval traces, MCP memory servers, and source lineage.

Agent memory needs a shared vocabulary because the same word can mean prompt history, product state, vector search, or user-specific facts. This glossary defines the terms used across Answer Engine content so engineers can evaluate memory systems by behavior instead of brand language.

Use this glossary with the Agent Memory guide, Inspectable Agent Memory, Supersession-Aware Memory, and Provable Forgetting. The definitions are grounded in current memory and context-engineering references, including the Model Context Protocol documentation, Anthropic’s context engineering guidance, LangChain memory concepts, and current research on LLM-agent memory systems (survey).

The glossary is intentionally conservative. It does not turn a concept into a shipped Answer Engine capability. Product pages and roadmap chips remain the source for what is available now.

Fig. 2 DefinedTermSet schema
FIG. 2

Glossary entries

Each term is a short, citable definition for an engineer or an AI answer engine. The coined terms link back into the Pillar 1 guide set.

agent-memory

Agent memory

A durable layer that stores scoped, source-linked facts and makes them available to agents across sessions, tools, and model calls.

short-term-memory

Short-term memory

Conversation or thread state that persists briefly but is not necessarily durable across tools or projects.

long-term-memory

Long-term memory

Stored context intended to survive beyond the current session and be recalled later under scope and policy controls.

episodic-memory

Episodic memory

Memory of events or interactions, such as a prior decision, support exchange, or coding session.

procedural-memory

Procedural memory

Memory of preferred processes, workflows, commands, or operating rules an agent should reuse.

source-memory

Source memory

Memory tied to documents, tickets, pages, transcripts, or artifacts that can be cited and inspected.

context-window

Context window

The temporary working space a model reads for one answer or bounded conversation.

context-engineering

Context engineering

The practice of choosing and shaping the information an agent receives so it can complete a task reliably.

retrieval-augmented-generation

Retrieval-augmented generation

A pattern where source material is retrieved and passed to the model so the answer can be grounded in evidence.

memory-write-path

Memory write path

The process that decides what should be remembered and records source, scope, type, and lifecycle metadata.

memory-read-path

Memory read path

The process that retrieves relevant memories, ranks them, and returns evidence to the agent or user.

memory-scope

Memory scope

The boundary that decides who or what can read a memory, such as tenant, workspace, library, user, or client.

tenant-isolation

Tenant isolation

A safety property where one tenant's memory cannot be retrieved or exposed inside another tenant's answers.

source-artifact

Source artifact

The canonical stored object, such as a document version or transcript segment, from which memory artifacts are derived.

provenance

Provenance

The origin and lineage of a memory, including the source system, artifact, version, and derivation path.

retrieval-trace

Retrieval trace

A record of the query, candidates, ranks, returned memories, citations, and answer path for one retrieval event.

inspectable-memory

Inspectable memory

Agent memory that exposes what was remembered, why it was retrieved, where it came from, and whether it is current.

black-box-memory

Black-box memory

Memory that influences answers without exposing source lineage, retrieval reasons, scope, or correction paths.

supersession

Supersession

A replacement relationship where a newer source or memory marks an older one as no longer current.

superseded-memory

Superseded memory

A remembered fact that remains inspectable as history but should not be treated as the current answer.

current-state-flag

Current-state flag

Metadata that marks whether a source artifact or memory should be treated as the current version.

decay

Decay

A memory lifecycle behavior where older or weaker signals become less likely to retrieve over time.

amnesia

Amnesia

A forgetting behavior that removes temporary conversational carryover without necessarily deleting source artifacts.

purge

Purge

A deletion behavior that removes or disables a source and the derived memory artifacts controlled by the system.

drift

Drift

A state where a source or memory changes without a clean replacement relationship, making recall suspect.

provable-forgetting

Provable forgetting

The ability to show that a memory and its derived artifacts were removed, disabled, or superseded under policy.

delete-handle

Delete handle

A durable identifier that lets a product target the source and derived artifacts affected by a deletion request.

tombstone

Tombstone

A record that marks a memory or source as removed or disabled so stale references do not continue serving.

derived-artifact

Derived artifact

A summary, embedding, tag, extracted entity, or citation object produced from a source artifact.

source-lineage

Source lineage

The chain from original source to stored artifact, derived memory, retrieval event, and cited answer.

mcp-memory-server

MCP memory server

A Model Context Protocol server that exposes memory tools to compatible agent clients.

context-pack

Context pack

A scoped bundle of retrieved evidence prepared for an agent to use in a task.

tool-call

Tool call

A structured request from an agent to an external tool, API, or MCP server.

agent-client

Agent client

The tool or runtime where the agent operates, such as Claude Code, Cursor, or another MCP-compatible client.

memory-portability

Memory portability

The ability to use, export, or migrate memory across agent clients and frameworks without lock-in.

no-training-default

No-training default

A product posture where customer memory is used for recall and product operation, not to train foundation models by default.

permission-aware-retrieval

Permission-aware retrieval

Retrieval that applies access scope before memories can be returned to an agent or answer.

retrieval-log

Retrieval log

A durable event record of what a memory system searched, retrieved, ranked, and returned.

memory-conflict

Memory conflict

A state where two or more memories disagree and the system needs inspection, supersession, or correction.

audit-trail

Audit trail

A record of memory actions, including writes, retrievals, corrections, deletion requests, and lifecycle changes.

roadmap-claim

Roadmap claim

A capability described as planned or shipping next rather than presented as available now.

Fig. 3 FAQPage schema / resource answers
FIG. 3

FAQ

What is this glossary for?

This glossary gives engineers concise definitions for agent memory terms used across Answer Engine guides and comparison pages.

Are the terms product claims?

No. The glossary defines concepts. Product pages label what is available now and what remains roadmap work.

Which terms matter most when evaluating vendors?

Start with inspectable memory, supersession, provable forgetting, source lineage, tenant isolation, and MCP portability.

NEXT

Use the terms as an evaluation rubric.

Start with inspectability, supersession, deletion posture, and MCP portability before you compare memory products by brand name.