Agents
Memory (AI)
AI memory refers to mechanisms that allow an agent to retain and retrieve information across steps or sessions. Short-term memory lives in the context window; long-term memory is externalized to vector databases, structured stores, or episodic logs that the agent queries at runtime.
Reliable long-term memory is the unsolved engineering challenge in production agent systems. Current best practice combines semantic retrieval (vector search over past interactions) with recency-weighted summarization to manage what fits in a finite context window.
Related terms
- AI Agent — An AI agent is a software system that takes a goal, plans a sequence of steps to reach it, executes those steps using tools (APIs, databases, browsers, code), and adapts when steps fail.
- RAG (Retrieval-Augmented Generation) — RAG is a pattern in which an AI model retrieves relevant documents from a knowledge base at query time and uses them as additional context to generate its response.
- Vector Database — A vector database is a database optimized for storing embeddings and answering similarity queries ("give me the 10 most similar items to this one").
- Context Window — A context window is the maximum amount of text (measured in tokens) that an AI model can process in a single inference call.