Semantic Memory (Agent)

Semantic memory in an AI agent is the storage of general world knowledge, domain facts, and declarative information that the agent can retrieve when needed.

It is typically populated via retrieval-augmented generation from a vector database and supplements the agent's base model knowledge with organisation-specific or up-to-date information. Because semantic memory is consulted as fact, an inaccurate entry keeps producing wrong answers until it is corrected.

Closely related concepts include Agentic Memory, Episodic Memory (Agent), Long-Term Memory (Agent), Agent Framework. Each is defined in the Prefactor glossary.