# Agent Memory glossary

Alphabetical definitions of terms used across SurrealDB Agent Memory architecture and memory docs.

Short definitions for terms that appear throughout the SurrealDB Agent Memory docs. For deeper treatment, follow the links where provided.

SurrealDB Agent Memory’s vocabulary is precise, but the intent is everyday: memory that **associates** related ideas (like hearing “cat” and thinking of pets, lions, or a nickname) and keeps **time and scope** straight (“I have one” versus “I used to” versus “they weigh about four kilos in general”). The entries below name the machinery; [What is SurrealDB Agent Memory?](/docs/agent-memory/welcome/what-is-surrealdb-agent-memory.md) and [Memory categories](/docs/agent-memory/mental-model/memory-categories.md) walk through the human-shaped examples.

## A

**Anaphora** - Pronouns and phrases in conversation that refer back to something said earlier (“he”, “that project”, “the policy we discussed”). Episodic memory keeps the transcript intact; extraction uses context to resolve what they mean.

**Attribute** - A named property on an entity (for example `role = Head of Platform`). Attributes can be superseded over time with `valid_from` / `valid_until`.

**Authoritative (pillar)** - Curated, vetted knowledge: handbooks, policies, product catalogues. Usually ingested as **documents** with higher default **trust**.

**Authority** - The policy that curated sources win over casual chat when sources conflict, implemented by the **reconciler** (often via **uncertainty** rather than silent overwrite).

## C

**Calibration (pillar)** - Gating assertions by confidence and trust; below a floor, SurrealDB Agent Memory refuses to overwrite and records uncertainty instead.

**Collective (pillar)** - Shared memory when multiple principals corroborate the same fact; independent assertions keep separate provenance. Automated promotion to wider scope is policy-gated.

**Confidence** - The reconciler’s posterior certainty on an assertion (`attribute.confidence`), stored separately from **source trust**.

**Context (read parameters)** - Optional **`labels`**, **`lens`**, and **`scope_view`** on `/query` and `/context` to filter or fold results within what your grant already allows. See [Contexts and scope](/docs/agent-memory/mental-model/contexts-and-scope.md#labels-lens-and-scope-views-reads).

**Consolidation (pillar)** - Background process that crystallises recurring observations into longer-lived beliefs.

**Context (category)** - Short-lived “what matters right now” for the active conversation.

**Context (tenant)** - A **Context** is SurrealDB Agent Memory’s top-level isolation unit: its own database, keys, and configuration. Not the same as the memory category “context”.

## D

**Decision trace** - A graph record of what the reconciler considered, created, or superseded during a write.

**Delegation** - Acting on behalf of another principal via **`X-Spectron-On-Behalf-Of`**, intersected with both parties’ grants (depth 1).

## E

**Elaboration (pillar)** - Background linking of related facts that were stored separately but belong together.

**Entity** - A typed node in the memory graph (for example `Person/alice`, `Product/airpods_pro`).

**Episodic (category)** - The raw ordered transcript of sessions and turns before extraction.

**Experiential (pillar)** - Knowledge from conversation and derived passes (`turn`, `reflect`, `elaboration`, …), usually lower default trust than authoritative material.

**Extraction** - The pipeline that turns text into entities, attributes, relations, instructions, and uncertainties.

## F

**Forget** - Explicit soft-removal of matching memory (`valid_until`), distinct from aging.

## I

**Identity (category)** - Stable facts about who the principal is (name, role, employer).

**Instructions (category)** - Behavioural preferences (“use British English”), applied at prompt assembly, not generic retrieval.

## K

**Graph edge kind** - A named structural signal used in document **`hybrid_graph`** retrieval (for example `knowledge_has_keyword`, `document_link`). Request and response enums reject unknown values with `400 Bad Request`.

**Known time** - When SurrealDB Agent Memory first recorded a belief; queried with `as_of`. See [Tri-temporal model](/docs/agent-memory/architecture/tri-temporal-model.md).

**Knowledge (category)** - Facts learnt in conversation, distinct from uploaded manuals.

**Memory category** - On extracted entities, attributes, and relations: `identity`, `knowledge`, or `context` (API-enforced enum).

## P

**Principal** - An actor (human, agent, service) that can be granted read/write permissions on scope paths.

**Provenance** - Structured metadata on every fact: source kind, reference, span, trust, derivation. See [Provenance and traceability](/docs/agent-memory/mental-model/provenance-and-traceability.md).

## R

**Reconciliation** - Comparing new extractions to existing memory: supersede, merge, or emit **uncertainty**.

**Reflection (pillar)** - On-demand synthesis from a question; results stored with lower default trust.

**Response trace** - Record of a composed answer (`/chat`, `/reflect`), used for tier-2 reuse when still valid.

**Retrieval trace** - Record of a `/query` (or related read): candidates, signals, tier, and results.

## S

**Scope** - Hierarchical slash paths (`org/acme/user/alice/`) that partition data within a Context. Register with `spectron scopes create` before use. Distinct from **permissions** and from **labels** (`key=value` descriptors).

**Session** - A conversation container: ordered **turns**, scope, and metadata.

**Source.kind** - Whether a fact came from a `document`, `turn`, `reflect`, `elaboration`, `consolidation`, and so on.

**Source.span** - Character positions in the originating message or passage for quotable citations.

**Source.trust** - Default weight reflecting how authoritative the source stream is (document versus casual turn, and so on).

**Supersession** - Replacing a prior assertion by setting `valid_until` on the old record while keeping history.

**System time** - Database MVCC history: what was stored at an instant. See [Tri-temporal model](/docs/agent-memory/architecture/tri-temporal-model.md).

## T

**Trace layer** - Memory about how memory was used: retrieval, decision, and response traces.

**Trust** - See **source.trust** and **calibration**; central to why curated and conversational facts combine safely.

**Turn** - One message in a session (`user`, `assistant`, `system`, `tool`).

**Tri-temporal** - System, known, and valid time kept distinct. See [Tri-temporal model](/docs/agent-memory/architecture/tri-temporal-model.md).

## U

**Uncertainty (category)** - Explicit “we do not know” or conflict records instead of guessed fill-ins.

**Unified graph** - One SurrealDB store for documents, turns, entities, relations, and traces. See [Unified substrate and authority](/docs/agent-memory/mental-model/two-layer-architecture.md).

## V

**Valid time** - When a fact held in the real world (`valid_from` / `valid_until`), independent of when SurrealDB Agent Memory learnt it.