Retrieval & Agents

Agent Memory

The mechanisms that let an AI agent remember things across steps or sessions, beyond what fits in one context window.

Because the context window is finite and resets, memory is what gives an agent continuity. Short-term memory lives in the current context as the running conversation and scratchpad, while long-term memory is stored outside, often in a vector database, and retrieved when relevant. Good memory lets an agent recall earlier decisions, user preferences, and facts it learned, which is essential for multi-step and long-running tasks.