Definition
Agent memory refers to the mechanisms that allow AI agents to retain and recall information across conversations and sessions. Short-term memory holds context within a single conversation. Long-term memory persists across sessions using vector databases, file systems, or key-value stores.
Example
An agent that remembers your preferred communication style, past project decisions, and client preferences without you having to repeat them every time you start a new conversation.
Why it matters
Without memory, every interaction starts from zero. With memory, agents build context over time and get progressively better at their jobs. Shogo agents learn from every interaction and improve continuously.