Interface: CognitiveMemoryConfig

Defined in: packages/agentos/src/cognition/memory/core/config.ts:245

Properties

agentId

agentId: string

Defined in: packages/agentos/src/cognition/memory/core/config.ts:253

---

archive?

optional archive: IMemoryArchive

Defined in: packages/agentos/src/cognition/memory/core/config.ts:370

Optional memory archive, read by CognitiveMemoryManager.rehydrate(), which returns a trace's archived verbatim content.

The manager hands this archive to neither the temporal-gist mechanism nor its consolidation pipeline, so setting it does not make gisting keep a verbatim copy.

Default

undefined (no archive; rehydrate() returns null)

See

IMemoryArchive, the archive contract, exported from @framers/agentos/memory/archive/IMemoryArchive

---

brain?

optional brain: Brain

Defined in: packages/agentos/src/cognition/memory/core/config.ts:328

Optional Brain instance for durable persistence.

When provided, memory traces, knowledge graph nodes/edges, prospective items, and observation pipeline state are persisted to the brain's SQL tables via sql-storage-adapter. The in-memory vector index remains the hot read path; Brain is the durable backing store that survives process restarts.

Falls back to in-memory-only storage when omitted.

Default

undefined (in-memory only)

See

Brain — the cross-platform persistence layer

---

cognitiveMechanisms?

optional cognitiveMechanisms: CognitiveMechanismsConfig

Defined in: packages/agentos/src/cognition/memory/core/config.ts:288

Optional per-mechanism cognitive science extensions (reconsolidation, RIF, FOK, etc.).

---

collectionPrefix?

optional collectionPrefix: string

Defined in: packages/agentos/src/cognition/memory/core/config.ts:298

Default

'cogmem'

---

consolidation?

optional consolidation: Partial<ConsolidationConfig>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:275

---

decay?

optional decay: Partial<DecayConfig>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:266

---

embeddingManager

embeddingManager: IEmbeddingManager

Defined in: packages/agentos/src/cognition/memory/core/config.ts:250

---

enableGraphActivation?

optional enableGraphActivation: boolean

Defined in: packages/agentos/src/cognition/memory/core/config.ts:311

Step 13: enable graph activation. Propagates to MemoryStoreConfig.enableGraphActivation. When true, the internal MemoryStore upserts entity nodes + related_to:co_occurs edges at encode time (from trace.entities), and seeds Anderson spreading activation from query-extracted entities at retrieve to compute the sixth composite-scoring signal. Default: false (legacy behavior, graphActivation signal is a silent zero).

Default

false

---

encoding?

optional encoding: Partial<EncodingConfig>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:265

---

featureDetectionLlmInvoker()?

optional featureDetectionLlmInvoker: (systemPrompt, userPrompt) => Promise<string>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:262

Required when strategy is 'llm' or 'hybrid'.

Parameters

systemPrompt

string

userPrompt

string

Returns

Promise<string>

---

featureDetectionStrategy

featureDetectionStrategy: "hybrid" | "llm" | "keyword"

Defined in: packages/agentos/src/cognition/memory/core/config.ts:260

Default

'keyword'

---

graph?

optional graph: Partial<MemoryGraphConfig>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:274

---

infiniteContext?

optional infiniteContext: Partial<InfiniteContextConfig>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:292

Infinite context window config. Enables transparent compaction for forever conversations.

---

knowledgeGraph

knowledgeGraph: IKnowledgeGraph

Defined in: packages/agentos/src/cognition/memory/core/config.ts:248

---

maxContextTokens?

optional maxContextTokens: number

Defined in: packages/agentos/src/cognition/memory/core/config.ts:294

Max context window size in tokens (required for infinite context).

---

moodProvider()

moodProvider: () => PADState

Defined in: packages/agentos/src/cognition/memory/core/config.ts:256

Callback to get current mood from MoodEngine or similar.

Returns

PADState

---

observer?

optional observer: Partial<ObserverConfig>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:272

---

persistAccessState?

optional persistAccessState: boolean

Defined in: packages/agentos/src/cognition/memory/core/config.ts:340

Keeps each trace's stability, access count, reinforcement interval and next reinforcement time across a restart: written to the Brain (with no Brain, to the vector store's metadata) at every access and read back at load (MemoryStoreConfig.persistAccessState). false writes and loads them as before, for one release of before-and-after measurement.

Default

true

---

persistentMemory?

optional persistentMemory: PersistentMemorySource

Defined in: packages/agentos/src/cognition/memory/core/config.ts:284

Optional persistent markdown memory source injected into every prompt.

This is separate from active working memory: working memory is the bounded cognitive focus, while persistent memory is durable agent/user state such as profile notes, preferences, and identity anchors.

---

reflector?

optional reflector: Partial<ReflectorConfig>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:273

---

rerankerService?

optional rerankerService: RerankerService

Defined in: packages/agentos/src/cognition/memory/core/config.ts:356

Optional reranker service for post-retrieval quality improvement.

When provided, retrieved memory traces are reranked after the cognitive scoring pipeline (vector similarity + strength + recency + emotional congruence + graph activation + importance). The reranker score is blended with the existing composite score at a 0.7/0.3 weighting to preserve cognitive signals while boosting semantically relevant results.

Recommended: Cohere rerank-v3.5 primary, LLM-Judge fallback.

Default

undefined (no reranking)

---

tokenBudget?

optional tokenBudget: Partial<MemoryBudgetAllocation>

Defined in: packages/agentos/src/cognition/memory/core/config.ts:269

---

traits

traits: HexacoTraits

Defined in: packages/agentos/src/cognition/memory/core/config.ts:254

---

typedNetwork?

optional typedNetwork: TypedNetworkRuntimeConfig

Defined in: packages/agentos/src/cognition/memory/core/config.ts:388

Stage E: optional Hindsight 4-network typed observer wiring.

When provided, encode() additionally extracts typed facts (World / Experience / Opinion / Observation banks) via the configured LLM and persists them in an in-memory TypedNetworkStore. retrieve() runs typed-graph spreading activation ('full' variant only) and produces a 4-way RRF fused ranking that's merged into the existing scoring.

Variants:

• 'minimal': bank routing + observer only (no graph traversal at retrieve).
• 'full': minimal + spreading activation per Hindsight Eq. 12 + 4-way RRF.

Default

undefined (Stage E disabled, zero-cost no-op)

See

packages/agentos-bench/docs/specs/2026-04-26-hindsight-4network-observer-design.md

---

vectorStore

vectorStore: IVectorStore

Defined in: packages/agentos/src/cognition/memory/core/config.ts:249

---

workingMemory

workingMemory: IWorkingMemory

Defined in: packages/agentos/src/cognition/memory/core/config.ts:247

---

workingMemoryCapacity?

optional workingMemoryCapacity: number

Defined in: packages/agentos/src/cognition/memory/core/config.ts:268

Default

7 (Miller's number)