Demos by HeyGen, Vapi, Modal.

Your AI agent doesn't only generate text anymore. It speaks, creates video, & runs complex compute. Welcome to Durable Multimodal AI.

Join us for the next edition of the Durable AI Meetup series-this time exploring what happens when AI agents go beyond text & into voice, video, & serious compute. And more importantly: how do you make all of that reliable in production?

What's Happening:

Lightning talks & demos from builders shipping multimodal AI in production

Networking with engineers & founders working on the next generation of AI applications

Korean street food, BOBA, & real technical conversations

Agenda:

5:30 PM - Doors open | Food, drinks, networking

6:00 PM - Introductions & Welcome

6:15 PM - Talks & demos begin

HeyGen

Vapi

Modal

7:00 PM - Open Networking w/ Food & Drinks

8:00 PM - Close

Who Should Come:

Engineers building AI agents that go beyond text (voice, video, multimodal)

Developers evaluating production infrastructure for AI workloads

Founders & builders curious about what multimodal AI looks like in production

Anyone who's asked "how do I make this actually reliable at scale?"

About the Companies:

Temporal - Durable Execution platform that ensures your AI agents & workflows survive failures, handle long-running operations, & reliably complete-even when things go wrong.

HeyGen (HyperFrames) - Open-source framework originated by HeyGen that lets AI agents compose videos by writing HTML, CSS & JS. Apache 2.0 licensed, built for the community.

Vapi - Build & deploy voice AI agents in minutes. Trusted by Amazon Ring, Intuit, & ServiceTitan. 1 billion+ calls supported, 99.9% uptime, 2.5M+ agents launched.

Modal - the cloud platform for AI development. Run inference, training, & batch workloads on any GPU, at any scale - with a dev experience that feels local. Teams like Runway, Suno, & Cognition who used to live in infra now ship faster.

Hosted by Temporal