​Description

​An agent can remember the facts of a task and still lose track of its work. Join Tokyo AI (TAI) for an evening on agent memory, execution state and recovery: what to retain for reasoning, what to record reliably, and how to continue after interruption.

​Designed for engineers building and operating agents, application architects and technical leads, this event connects memory and retrieval choices with the reliability requirements of long-running systems.

​Melanie Warrick, working on AI developer relations engineering at Temporal, will present What an Agent Needs to Remember, including a live demo. Koji Annoura will present Different Agents, Shared Memory: Building Persistent Context with Neo4j, demonstrating shared context across agents with Neo4j and MCP. Yulan Yan of Zilliz will present Agent Memory in Production: Patterns from Real-World AI Applications, examining patterns from production AI applications.

​When: Wednesday, October 14, 2026, 18:00-21:00 JST.
Where: Tokyo, venue to be announced.

​Agenda

​Each talk slot includes Q&A.

• ​18:00 - Doors open

• ​18:25-18:30 - Welcome

• ​18:30-19:00 - What an Agent Needs to Remember (Melanie Warrick)

• ​19:00-19:30 - Agent Memory in Production: Patterns from Real-World AI Applications (Yulan Yan)

• ​19:30-20:00 - Different Agents, Shared Memory: Building Persistent Context with Neo4j (Koji Annoura)

• ​20:00-21:00 - Networking

• ​21:00 - Doors close

​Talks

​What an Agent Needs to Remember

​Speaker: Melanie Warrick (AI & DevRel Engineer, Temporal)

​Abstract:

​Ask what an agent should remember and you’ll usually hear about working, episodic, semantic, and procedural memory. These describe information available to the agent as it reasons. But an agent can remember every fact about a task and still forget where it is in the task.

​Production agents also need reliable execution state: which tools ran, which side effects occurred, what a person told the agent, what work completed, and what should happen next. This talk distinguishes what an agent knows from the state of its work and explains why they have different correctness requirements. A live demo makes the distinction visible: an agent that remembers everything about its task but still cannot tell whether it already performed an action.

​Then we’ll take the problem into long-running agents, where preserving execution history creates another challenge: the history itself can become too large. Temporal provides the durable execution examples, but the architectural question applies more broadly: what must a system preserve so an agent can resume its work, not just recall what the work was about?

​Bio:

​Melanie Warrick works on AI developer relations engineering at Temporal, focused on building reliable AI systems and agents. She is also co-founder and CTO of Fight Health Insurance, an AI platform that helps people appeal denied US health insurance claims.

​Melanie has worked in AI for more than a decade, from implementing an open source neural networks platform (Skymind) and fine-tuning domain models (FHI) to deploying AI applications in production. Her broader engineering background spans distributed systems, developer infrastructure, and health tech, including work at Google Cloud and engineering leadership at startups.

​Agent Memory in Production: Patterns from Real-World AI Applications

​Speaker: Yulan Yan (Solutions Architect, Zilliz)

​Abstract:

​Agent memory can mean very different things depending on the product: retaining past conversations, consolidating interactions into higher-level profiles, reusing prior task experience, or keeping years of personal history available for future interactions.

​This talk shares several real-world production systems across AI companions, enterprise agents, robotics, and personal AI devices, where Milvus and Zilliz Cloud serve as the vector database layer for memory storage and retrieval. From these cases, I distill four recurring patterns and look at the design choices behind them: what the unit of memory is, when raw interactions are consolidated, which outcomes are written back, and how recent and older memories are prioritized.

​I’ll close with the production considerations that cut across these patterns, including retrieval, freshness, updates, isolation, and lifecycle management, and how Milvus and Zilliz Cloud support these requirements in production.

​Bio:

​Yulan Yan is a Founding Solutions Architect at Zilliz. She previously worked as an NLP researcher and Data & AI Solutions Architect, and now focuses on vector databases and production architectures for search, retrieval, and AI agents.

​Different Agents, Shared Memory: Building Persistent Context with Neo4j

​Speaker: Koji Annoura (Co-founder, Neo4j Users Group Tokyo)

​Abstract:

​An agent can remember the context of a task, but that context is often tied to a particular agent, model, or session. When the model changes or another agent takes over, useful knowledge can easily be lost or reconstructed differently.

​This talk looks at what should remain outside individual agents. Instead of treating memory only as something inside an agent, shared knowledge can be stored as persistent context: entities, relationships, evidence, and changes that multiple agents can access and reuse. A graph provides a natural way to keep not only facts, but also how those facts are connected and where they came from.

​Using Neo4j, I’ll demonstrate a simple shared context graph and show how different agents can read and update the same knowledge through MCP. The broader question is how to give agents access to durable knowledge that can survive a single model, agent, or session while still allowing each agent to reason in its own way.

​Bio:

​Koji Annoura is an independent consultant based in Japan, working with knowledge graphs, graph databases, GraphRAG, SQL/PGQ, and MCP. He has more than 40 years of experience in software and data systems.

​He co-founded the Neo4j Users Group Tokyo in 2013 and is a Neo4j Ninja. He regularly speaks at open source, database, and graph technology conferences in Japan and internationally, with a recent focus on how knowledge can be kept independent of individual AI models and reused across systems.

​Organizers

​Ilya Kulyatin is an entrepreneur with work and academic experience in the US, Netherlands, Singapore, UK, and Japan. He holds a BA in Economics, an MA in Finance, and an MSc in Machine Learning. He's a 3x founder, now helping Japan grow the local AI ecosystem through a not-for-profit community, Tokyo AI (TAI), while building an AI-native system integrator and solutions provider, Foundry Labs株式会社.

​Supporters

​Foundry Labs K.K. is a Tokyo-based AI systems integrator and solutions provider, delivering end-to-end support for enterprises: from strategy design through implementation, deployment, and operations. They tailor AI to each client's operational, regulatory, and security requirements, with hands-on experience across finance, government, and industry, and a track record of shipping production systems in secure and regulated environments.

​About TAI

​Tokyo AI (TAI) is the largest international AI community in Japan, with 5,000+ members mainly based in Tokyo: engineers, researchers, investors, product managers, and corporate innovation leaders. Through 80+ events a year and 300+ speakers spanning startups, enterprises, and academia, TAI connects the people building AI in Japan with the global ecosystem, working to transform Tokyo into a global AI hub.

​Privacy Policy

​We will process your email address for the purposes of event-related communications and ongoing newsletter communications. You may unsubscribe from the newsletter at any time. Further details on how we process personal data are available in our Privacy Policy.