Memory Types

Agent memory systems are categorized into distinct types that mirror concepts from cognitive science, each solving a different persistence and retrieval challenge. Short-term memory (conversation history within a session) provides immediate context; working memory (scratchpads, state variables) tracks in-progress task state; long-term memory (vector databases, knowledge bases) persists across sessions; and episodic memory (past interaction logs) enables agents to learn from previous experiences. Understanding these memory categories is foundational because choosing the right type for each piece of information determines whether your agent can maintain coherent state across complex multi-step tasks. The architectural decision of what to remember, for how long, and how to retrieve it is one of the most impactful design choices in any agent system. This concept connects to short-term memory and long-term memory for specific implementations, memory management for strategies around when to store and evict, and vector databases for the primary infrastructure behind long-term retrieval.