glossary

Agent memory

learn /definition

Agent memory is persistent, retrievable knowledge that carries across AI sessions: what past runs learned, what was decided and why, and where things live, recalled before acting rather than rediscovered.

It is distinct from two things it is often confused with. Context windows are working memory: everything in them evaporates when the session ends. And retrieval over documents (RAG) recalls what the organization wrote, but not what the agents themselves learned by doing the work.

Useful agent memory splits WHAT from WHERE. Knowledge (a decision, a correction, a learned constraint) ranks by relevance, importance, and recency. Location (which file, which module, which doc) is a map that spares the agent re-exploring territory it has already covered.

The capture side matters as much as recall: memory written automatically from everything becomes noise, and memory that depends on someone remembering to save it becomes empty. The durable pattern wires capture into the process itself, at the steps where decisions actually happen.