Memory for LLMs

Join us for an evening of deep-dive technical talks on LLM Memory—moving beyond context windows to build persistent, context-aware AI applications that scale.

As Large Language Models evolve, the real challenge isn't just generating text—it's remembering context, maintaining state, and managing historical data effectively. How do you provide LLMs with persistent, long-term memory without overwhelming context limits or skyrocketing latency and costs?

Whether you're building stateful AI agents, implementing advanced Retrieval-Augmented Generation (RAG), or managing enterprise-grade vector and relational data, this meetup covers the practical architectures and trade-offs behind modern LLM memory systems.

What We'll Cover

• Architectural Patterns for LLM Memory: Moving from simple in-memory context windows to scalable, persistent data layers.

• Database & Vector Strategies: How distributed databases and specialized storage handle real-time vector embeddings, chat histories, and state management.

• Production Engineering Insights: Lessons learned, common pitfalls, and real-world implementations for stateful AI applications.

Agenda

• 5:30 PM – 6:00 PM: Networking, Food & Drinks 🍕🥤

• 6:00 PM – 6:10 PM: Welcome & Opening Remarks

• 6:10 PM – 6:40 PM: Talk 1: Heather Downing (30 mins incl. Q&A)

• 6:40 PM – 7:10 PM: Talk 2: Ben Kearns (30 mins incl. Q&A)

• 7:10 PM – 7:40 PM: Talk 3: Arshan Ommid (30 mins incl. Q&A)

• 7:40 PM – 8:00 PM: Open Q&A, Networking & Wrap-Up

Complimentary food and beverages will be served on-site!

Speakers

• Heather Downing – Developer Advocate at YugabyteDB

  • Connect on LinkedIn: linkedin.com/in/heathermdowning

  • Bio: Heather is an experienced Developer Advocate and engineer passionate about distributed databases, cloud architecture, and modern backend systems. At YugabyteDB, she helps developers build resilient, scalable data infrastructures for modern applications.

• Ben Kearns – CTO & Founder at Ferrosa & Grounded Health

  • Connect on LinkedIn: linkedin.com/in/benjaminkearns

  • Bio: Ben is a technology leader and entrepreneur focused on building intelligent healthcare and enterprise AI solutions. With deep hands-on expertise in machine learning and backend architecture, he specializes in bringing complex AI systems into production.

• Arshan Ommid – Founding Sales, GTM & Strategic Partnerships

  • Connect on LinkedIn: https://www.linkedin.com/in/arshan-ommid-93782bb0/

  • Bio: Arshan is an entrepreneur and go-to-market leader with experience spanning strategic partnerships, healthcare technology, and biomedical innovation. He has built and led early-stage ventures and brings a founder’s perspective on turning emerging technologies into practical products and scalable businesses.

Who Should Come

This event is ideal for:

• AI & ML Engineers building LLM-powered applications, agents, or RAG pipelines.

• Software Engineers & Architects interested in state management, vector databases, and distributed storage.

• Tech Founders & Engineering Leaders looking to understand production-grade AI stack trade-offs.

• Developers curious about the practical future of generative AI architecture.

About AAIF

The Agentic AI Foundation (AAIF) is a community dedicated to advancing the understanding and practical application of agentic AI. We bring together engineers, researchers, founders, builders, and AI enthusiasts to explore how autonomous AI systems are designed, evaluated, and deployed.

Through reading groups, workshops, and community discussions, AAIF brings together engineers, researchers, founders, and AI enthusiasts to exchange ideas, challenge assumptions, and learn from one another.

By attending you agree to our Code of Conduct and Privacy Policy.