28 days ago

Announcing the Challenge Winners

The Gemini Live Agent Challenge Winners! 🏆

Congrats again to everyone who submitted a project in this challenge! You didn't just build apps—you built the future of agentic AI. You moved past the "chat box" and proved that the next generation of software will see, hear, and interact right alongside us.

Now, please join us in celebrating our winners!

🌟 The Grand Prize

ORION - Operating Room Intelligent Orchestration Node 

🥇 Category Winners
  • Best of Live Agents: drone-copilot – A masterclass in real-time interaction and low-latency feedback.

  • Best of Creative Storytellers: Sankofa – Beautifully executed interleaved output that weaves…

Read more


2 months ago

Submissions are Locked! 🔒

First and foremost—take a breath. The hard part is over. Thank you for the incredible amount of time, late-night coding, and creative energy you’ve poured into the Gemini Live Agent Challenge. We’ve been watching the projects roll in, and the level of multimodal innovation is truly inspiring.

⏸️ Submissions are locked in
  • No More Edits: Please refrain from making any changes to your linked code repositories.

  • Keep Building (Separately): If you’re excited to keep evolving your agent beyond the hackathon—which we love to see!—please fork your repository. Continue your new work in the fork, but keep the original repo exactly…

Read more


2 months ago

⏱️ The Final Sprint: Polishing Your Gemini Live Agent for the Win

Hey everyone, 

As we approach the deadline (only 3 days to go!), the "feature creep" is real, and the deadline is looming: March 16th at 5:00 PM PT.

At this stage, the best projects shift from building to storytelling and stability. Here are some "pro-tips" to ensure your multimodal agent stands out to the judges in these final days.

Don’t forget: ALL Projects must meet the following three criteria at minimum: 

  1. Leverage a Gemini model

  2. Agents must be built using either Google GenAI SDK OR ADK (Agent Development Kit)

  3. Use at least one Google Cloud service (deployed on Google…

Read more


3 months ago

What are you building for? $80,000+ in prizes

Hey Builders,

We are officially half way through the challenge, and the competition is heating up. We want to make sure you know exactly what’s on the line.

Cash, Credits, and a Trip to Las Vegas? See the Prize Pool 🎰

Grand Prize

  • $25,000 in USD

  • $3,000 in Google Cloud Credits for use with a Cloud Billing Account

  • Virtual Coffee with a Google Team Member

  • Social Promo

  • Maximum of two (2) Google Cloud Next 2026 conference tickets for two (2) teammates (April 22-24, 2026) (Value: $2,299 each)

  • Maximum of two (2) travel stipends for airfare and hotel to Google Cloud…

Read more


3 months ago

🛑 Stop typing, and start interacting! | Get building for the Gemini Live Agent Challenge

Hey builder! 🛑 Stop typing, and start interacting!

You’ve officially joined the movement to move beyond the text box. The future isn’t about just chatting with AI—it's about immersive, real-time experiences that See, Hear, Speak, and Create.

Your Immediate Mission:

Choose one of our three categories to plant your flag:

  1. Live Agents 🗣️: Real-time audio and vision interaction.

  2. Creative Storyteller ✍️: Multimodal storytelling with interleaved output.

  3. UI Navigator ☸️: Visual UI understanding & interaction.

Find examples and specifics on each category.

Get Set Up Right:

  • Join the Discord: Great teams are built in the chat. Find your co-founder

Read more


3 months ago

Your Roadmap for the Gemini Live Agent Challenge

🛠️ Choose Your Path: The Three Pillars

Before you write a single line, you need to plant your flag in one of these three categories. Which one speaks to your inner architect?

  • The Live Agent: Focus on the Live API. Think voice-enabled tutors that "see" a student's sketchbook or a support agent that doesn't freak out when you interrupt it.

  • The Creative Storyteller: This is about Interleaved Output. Don't just generate text; weave a tapestry of narration, inline imagery, and video in one fluid stream.

  • The UI Navigator: Use Gemini's multimodal power to interpret screens. Build an agent…

Read more