Knowledge-Graph Memory

memory pattern · maturity: emerging · risk: medium

Memories stored as entities and typed relations rather than documents: recall traverses structure (who owns what, what depends on what) instead of matching text.

When to use

Question shapes flat stores cannot answer: relationships, dependencies, and multi-hop connections across memories.

Specification

Memory typesemantic
Storagegraph database or graph layer over extracted entities
Retrievalgraph traversal and structured query, often combined with embeddings
Update methodpipeline-extracted from content; human or agent curation of the schema
Decay / staleness handlingEdges can carry validity intervals (see zep's temporal model), which is the strongest freshness story in any memory architecture when actually implemented.
Risk level / maturitymedium / emerging

Privacy and safety

Graphs make inference easy by design; linked innocuous facts can compose into sensitive ones. Access control must consider paths, not just nodes.

Failure modes

  • Extraction errors become structural errors
  • Schema rigidity fighting a changing domain
  • Build cost dwarfing the query shapes actually used

Assessment

The high-ceiling architecture: qualitatively better recall when extraction lands, structural errors when it misses. Adopt for the question shapes, not the aesthetics; most projects' questions are flatter than they think.

Evaluation method: Multi-hop question accuracy against a labeled set; extraction precision audit.

Go deeper