One Fact per Vector: What Chunk Granularity Does to Agent-Memory Recall, Measured on Three Local Embedders (2026)

An agent memory store is usually built by a chunker that nobody re-examines after the first week. One vector per conversation turn, per note, or per fixed block of text. The store looks healthy, because the questions used to check it are single-fact questions about a short note, and those pass at almost any granularity. Then a user asks a two-part question — “how do access-token and signing-key lifetimes compare?”, “who owns the deploy key and how often does it rotate?” — and the retriever returns one half of the answer with no error at all. The other half is in a different chunk and did not fit in the top-k. ...

November 15, 2026 · 12 min · baeseokjae