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

Swap the Embedding Model, Keep the Store: Agent Memory That Returns the Wrong Neighbour Without an Error

An agent memory store can survive an embedding-model change while quietly returning the wrong fact. Nothing in the stack raises, because nothing in the stack compares the encoder that wrote a vector with the encoder that now reads it. In a 40-document fixture with 15 single-answer queries, one encoder on both sides ranked the labelled document first for 15 of 15 queries. Replacing the document encoder with a different model of the same width dropped that to 1 of 15, and no call failed. Replacing it with a model of a different width failed all 15 queries with a length error — the loud case, and the easy one. ...

November 2, 2026 · 12 min · baeseokjae