Protocol Demo Night at WorkOS (MCP, A2A, AG-UI)
AI Tinkerers SF Meetup: Protocol Demo Night @ WorkOS
Protocol Demo Night dives into the emerging world of AI protocols — the standards and layers powering the next generation of agent systems. Expect fast-paced live demos showing how protocols like A2A, MCP, and AG-UI unlock interoperability and new capabilities.

Event Details
Date & Time
- Thursday, October 9th, 2025 · 6pm–8pm
Location
- WorkOS HQ, San Francisco, CA
Capacity
- 150
Registration
- RSVP here: Register Here
What to Expect
- 🍕 Networking & pizza at 6:00
- ⚡ Lightning demos :
Submit a Demo
Got a protocol-related project to show?
👉 Apply here: Demo Proposal Form
All demos are 5–10 min, code-first, no slides.
Sponsors
WorkOS – APIs for enterprise-ready apps
CopilotKit – Framework for in-app AI copilots, creators of AG-UI
Composio – AI agent toolkit & integration platform
(Sponsorships still open: Become a Sponsor)
📊 AI Tinkerers SF Stats
- Attendees: This exclusive community of 7,284 technical professionals comprises 45% machine learning specialists, 40% agentic systems builders, and 30% infrastructure engineers. Distinguished by a 30% founder-to-member ratio and researchers from Google DeepMind and Meta, members actively pioneer real-world autonomous agents, custom Model Context Protocol servers, and hardware-accelerated AI.
- Companies Represented: Featuring tech giants like Google DeepMind, Meta, and Apple, alongside industry leaders such as Amazon, Stripe, and Uber, and rising AI startups like Wordware, Chroma, Replicate, and ElevenLabs, and more
- Demos: 487 demos were submitted and 172 were accepted and presented. The most compelling themes covered agent-native product UX, real-time multimodal voice/vision experiences, and protocol-driven integrations (especially MCP). Technical exploration has also emphasized reliability via tracing/evals and verification, grounding via advanced retrieval/context strategies, and security-focused agent infrastructure including safe tool access, privacy controls, and human-in-the-loop patterns.