The Generative UI Hackathon (A2UI, AG-UI, MCP Apps) [AI Tinkerers - San Francisco]

The Generative UI Hackathon (A2UI, AG-UI, MCP Apps)

May
09
Saturday
Saturday, May 9th, 2026 12PM to 6PM (PDT)
Address Info
Available on RSVP acceptance

Event Ended

This event has already taken place.

Attendees 286+ registered
Our attendees include engineering leaders and founders from Microsoft, Meta, and Amazon, bringing deep expertise in AI/ML, Python, and full-stack development.

(Banner) A promotional banner for the 'Generative UI Global Hackathon' focused on 'Agentic Interfaces', scheduled for May 2026. Text: Saturday, May 9th, 2026 Generative UI Global Hackathon Agentic Interfaces 15+ CITIES ACROSS THE WORLD CopilotKit Gemini AI TINKERERS LangChain Manufact Daytona Modern, clean, and tech-focused. | Colors: #000000, #38b2ac, #805ad5, #ffffff Note: The image is a digital graphic designed for event promotion, featuring a clear headline, date, and sponsor logos.

The Generative UI Hackathon (A2UI, AG-UI, MCP Apps)

All UI will be AI.

AI is changing how we interact with technology, and the Generative UI stack is emerging.

In this hackathon we will build cutting-edge Generative UI applications using Google’s A2U, CopilotKit’s AG-UI and MCP Apps.

Builders will be provided with a (optional) starter repo that connects this stack together, and includes all the relevant MCP servers and Agent skills, so you can focus on building and not set up.

It will also be kicked off by a talk from the creators of A2UI, AG-UI, MCP Apps, Manufact and LangChain.

They will walk through the Generative UI spectrum and help you think through what projects you can build.

This will be a part of a GLOBAL Hackathon, happening simultaneously across 18 cities on 4 different continents.

If you are interested in the future of UI and Generative Interfaces, this will be the place to be. Registration is limited. Only proven builders will be accepted.

The winning team will receive Mac Minis
The runner up team will receive Meta Ray Ban Glasses for their whole team.

Format

  • 12:00 PM - Doors open (check-in, food, team-up)
  • 12:30 PM - Global kickoff video: generative UI, the stack, the tracks
  • 1:00 PM - Build. Teams form, starter kits and credits distributed
  • 5:00 PM - Show and tell. 2-3 minute demos. Working code only.
  • 6:00 PM - Submissions close. Projects submitted to the hackathon platform.

Global Sponsors

Google DeepMind

Google DeepMind is the AI research lab behind Gemini and many of the open protocols defining how agents talk to interfaces, including A2UI - the open-source protocol letting agents send fully interactive UI components instead of plain text. Credits for participants distributed via the starter kit on event day.
(Logo) The official logo for Google DeepMind, featuring the multi-colored 'Google' brand name followed by 'DeepMind' in a solid dark grey font. Text: Google DeepMind Colors: #4285F4, #EA4335, #FBBC05, #34A853, #5F6368 Note: This is a clear, typographic brand identifier for a corporate entity, which fits the definition of a logo.

CopilotKit

CopilotKit is the Agentic Frontend Stack and the company behind the AG-UI Protocol.

Their React and Angular SDKs allow developers to build rich fullstack agentic applications with Generative UI that can leverage AG-UI, A2UI and MCP Apps.

They have 40k+ GitHub Stars Across their repos and their AG-UI protocol has been adopted by Google, AWS, Microsoft, Oracle, LangChain, Mastra, PydanticAI and more!

Starter templates, framework access, and full docs at docs.copilotkit.ai.
(Logo) The logo for CopilotKit, featuring the brand name in a dark purple font followed by a stylized kite icon in shades of blue and purple. Text: CopilotKit Colors: #120b3b, #2563eb, #7c3aed Note: The image displays a brand name alongside a graphic symbol, which is characteristic of a corporate logo.

Manufact

Manufact is the platform behind mcp-use, the fullstack open-source framework developers use to build MCP Apps for ChatGPT and Claude and MCP Servers for AI agents. The SDK ships in both TypeScript and Python with auto-discovery for interactive widgets, hot reload, and a built-in Inspector for testing. Manufact Cloud handles deployment, observability, and branch previews - push to GitHub and ship to production in under 60 seconds. Starter templates, the create-mcp-use-app scaffold, and full docs at github.com/mcp-use/mcp-use
(Other) A solid black rectangular image with no visible content. Note: The image consists entirely of a single solid black color with no identifiable subjects, text, or graphics.

Langchain

LangChain is the leading framework for building production-ready LLM applications-powering everything from simple chains to complex, stateful agents.

From orchestration and tool-calling to retrieval and memory, LangChain provides the primitives teams use to move beyond demos and into real systems. If you’re working on agents, RAG pipelines, or multi-step reasoning workflows, you’ve likely touched LangChain somewhere in your stack.

(Other) A solid black rectangular image. Note: The image is a plain, solid black rectangle with no identifiable features, text, or artistic elements that would place it into the other categories.

Daytona

Daytona is building the infrastructure layer for running code dynamically-ephemeral environments that spin up instantly, execute reliably, and disappear when you’re done.

If you’re working with agents that write and run code, sandboxing untrusted execution, or scaling developer workflows beyond local machines, Daytona is the kind of primitive you end up needing.

(Logo) A minimalist logo for 'Daytona' featuring a circular geometric icon and clean sans-serif typography. Text: Daytona Colors: #000000, #FFFFFF Note: The image displays a brand name alongside a specific graphical symbol, which is the defining characteristic of a logo.


Ready for more?

Check out other posts from this blog.

View all posts

Contact Organizers

Questions? We're here to help.