Comparison
Agent Memory vs Retrieval-Augmented Generation
Agent Memory and Retrieval-Augmented Generation are both common AI/LLM terms but cover different ideas. Here is a quick side-by-side.
When you would reach for Agent Memory
Agent Memory comes up when the question is fundamentally about agents & tools.
A chat product that remembers "the user prefers Python over JavaScript" across sessions via a vector-backed memory store.
When you would reach for Retrieval-Augmented Generation
When the model needs information that is not baked into its weights — fresh, private, or domain-specific.
"Chat with your PDFs" — Notion, Glean, ChatGPT custom GPTs.
Frequently asked
What is the difference between Agent Memory and Retrieval-Augmented Generation?
Agent Memory: Agent memory is the mechanism that lets an agent carry information across turns or sessions — short-term (current conversation context) or long-term (persistent facts about the user or world). Retrieval-Augmented Generation: RAG retrieves relevant documents from a corpus at query time and includes them in the prompt, letting an LLM answer with up-to-date, source-cited, private information without retraining.
When should I use Agent Memory vs Retrieval-Augmented Generation?
Agent Memory is the right concept when you are focused on agents & tools. When the model needs information that is not baked into its weights — fresh, private, or domain-specific.
Are Agent Memory and Retrieval-Augmented Generation the same thing?
No. Agent Memory is agents & tools; Retrieval-Augmented Generation is agents & tools. They are related but address different parts of the AI stack.