Agentic memory is storage, not RAM; however, the computer industry has been mixing up these two terms forever (see
storage vs. memory). The vector database and graph RAG (retrieval-augmented generation) are two types of storage used with AI agents.
A vector database, which converts text into math is good for questions and answers and more like regular database queries. To obtain answers, a straight-forward search is used. A graph RAG uses a knowledge graph to store entities and relationships. Good for reasoning, graph RAG results are made by traversing the graph. See
AI agent and
RAG.