AI Agents That Remember: Redis Agent Memory Explained

In this video, I show how to add long-term memory to AI agents using Redis Agent Memory Server, MCP tools and LangGraph. We start with the architecture: an A2A-capable server receives user messages, talks to the Redis Agent Memory API, uses MCP tools for memory creation, stores long-term memory in Redis, and uses a task worker for background memory processing. You will see how the different services fit together with Docker Compose, why Redis is used as memory and queue layer, and how an agent can retrieve and store user-specific information across conversations.