MemMachine: Agents That Learn, Memory That Lasts

Session Track: Graph Memory & Agents

Session Time: 10:30 am - 11:00 am April 15

Session description

Switching AI model providers (and even models) is hard, as you need to start from scratch and input your context every time you switch. This talk will introduce MemMachine, an open-source memory layer for AI agents. It enables AI-powered applications to learn, store, and recall data and preferences from past sessions to enrich future interactions.

Since it’s using Neo4j in the back to store and refine memories, this talk will focus on how our understanding of how to store, refine, and retrieve memories evolved over time and how we leverage Neo4j.

Speaker

Christian Kniep

Principal Architect, MemVerge

Christian is passionate about making complex IT systems easier to use. He started as an HPC Systems Engineer in the automotive industry and later became an InfiniBand SME, working on HPC interconnects in Paris. After Docker emerged in 2014, he returned to Berlin to work with containerized platforms at a startup, PlayStation Now, and Docker Inc. In 2019, he joined AWS as an EC2 Spot Specialist Solutions Architect and the first Developer Advocate in the HPC team. Since 2022, he has focused on containerized HPC and AI/ML, working at the Max Planck Institute and later joining MemVerge as Principal Architect.