Agent memory · Guide
What is agent memory?
Agent memory is durable state that helps an AI agent preserve useful facts, decisions, preferences, and project knowledge across sessions.
Agent memory is the durable state an AI agent can carry across sessions: useful facts, decisions, preferences, constraints, and project knowledge that should influence future work. It is different from a context window. Context is what a model can see now; memory is what the system has decided should remain useful later.
A practical agent-memory system needs more than storage. It needs a lifecycle: capture evidence, decide what deserves to persist, assign scope and lifetime, retrieve only what is relevant, preserve provenance, and replace or forget state when reality changes. A transcript records what happened. Memory is a maintained judgment about what the next agent should know.
After more than 1000 coding-agent sessions across Claude Code, Codex, Cursor, Pi, and OpenCode, I found the stable architectural boundary is user-owned state beneath replaceable models and harnesses. The detailed evidence, architecture, and failure modes are documented in my Agent Memory field report.