Letta

A technical mechanism for retaining, retrieving, and managing state across an AI agent's interactions over both short and long time horizons, simulating cognitive architectures.

The immediate, active context window space currently available for a Large Language Model's inference during a single interaction turn.

Externalized, persistent storage that allows AI agents to recall facts, user preferences, and historical context across separate execution sessions and vast timeframes.

A temporal log of an agent's past experiences, interactions, observations, and execution steps recorded in strictly chronological order.