We've been quietly building a graph-native memory layer for AI agents, and it's now far enough along to show. This is a walkthrough of the NAMS console — tab by tab — so you can see exactly what an agent's memory looks like when it lives in a graph.
Most agents you build today are amnesiacs. They run a chain of reasoning, return an answer, and forget the whole thing the moment the request ends. The usual patch — stuff transcripts into the context window, bolt on a vector store, write glue code to decide what to retrieve — works until the conversation gets long, the facts start to contradict each other, and you realize your "memory" is just a pile of text chunks ranked by cosine similarity.
The Neo4j Agent Memory Service (NAMS) is our take on a better foundation: persistent, structured memory for LLM agents, delivered as a managed cloud service. You call a REST API or connect an MCP client; NAMS handles storage, entity extraction, deduplication, e