Everyone's Trying Vectors and Graphs for AI Memory. We Went Back to SQL.

Everyone's Trying Vectors and Graphs for AI Memory. We Went Back to SQL.

Vector Stores Add Latency and Complexity For Most Agent Memory

The default in 2024 for agentic LLM memory is a vector DB with a glossy API claiming semantic search at scale. Docs hype embedding-powered lookups and treat SQL as legacy.

For most agentic workloads, that's backwards. Unless you're at hundred-million-vector scale, vector DBs add sync/async glue, ops overhead, surprising ANN recall quirks, and debugging headaches. You lose the ability to reason predictably about queries by user, timestamp, or tag.

Classic SQL wins when you need precise, scoped recall—"what facts are in my recent working memory, for topic X, since 10 minutes ago"—in a single query. Vector search gives you best-effort, top-k returns, often unstable when embeddings drift or you upgrade models. ANN recall is not a drop-in replacement for classic key+filter queries.