Long-term Memory
Persistent storage of information that an AI agent can retrieve across multiple sessions — not just within one conversation. Without it, every conversation starts from scratch. With it, an agent can remember your preferences, past decisions, ongoing projects, and context from weeks ago. Technically implemented as external storage (a database) that the agent reads from and writes to, not as anything built into the model itself.
In practice
You're building an AI assistant that should remember client preferences across sessions. When a client returns three weeks later, the assistant should know they prefer bullet points and hate jargon. Long-term memory is what makes that possible — storing relevant facts in a database and retrieving them when that client comes back.
Related concepts