Cactus x Google DeepMind Hackathon
Build agentic systems that run locally on-device using FunctionGemma on Cactus Engine, with seamless fallback to Gemini in the cloud.
Organized by
AI Tinkerers
Community Partner
AI Nexus
Presented by
Global Locations
Join us in person or online from anywhere in the world
San Francisco
California, USA
London
United Kingdom
Boston
Massachusetts, USA
Los Angeles
California, USA
DC/Maryland
USA
Singapore
Singapore
Online/Remote
Join from anywhere
What You'll Be Building
Create agentic applications that combine local execution with cloud intelligence
Local-First AI
FunctionGemma for fast, local execution on mobile devices and Macs using Cactus Compute as the runtime.
Cloud Fallback
Gemini APIs as a cloud fallback for more complex reasoning and heavy tasks when local processing isn't sufficient.
The Goal
Design systems that intelligently decide where computation should happen — locally or in the cloud — based on context, cost, latency, and capability.
Example Directions
Offline-first AI assistants with cloud escalation
Local agents coordinating tools and workflows
Privacy-preserving AI apps that minimize data exfiltration
Hybrid inference pipelines across edge + cloud
Event details
Everything you need to know about the hackathon
When
Saturday, February 21, 2026
8:30 AM - 8:30 PM PST
Where
6 cities worldwide
Plus online/remote option
Who
Senior engineers, technical founders, ML/infra engineers
Teams of 1-4 builders
Schedule
How Teams Work
Team Formation
Teams of 1-4 builders. Solo builders are welcome! You can arrive with an idea or form one on the spot.
Submission Requirements
All teams must submit:
- A working demo
- A short explanation of architecture & trade-offs
- Clear use of FunctionGemma and/or Gemini
What You'll Get
Direct access to DeepMind and Cactus Compute technical context
A high-signal room of builders who ship
Real-time feedback on your architecture and design decisions
Exposure for standout projects across the AI Tinkerers network
Prizes and recognition for top teams (details announced on-site)
Most importantly: You'll leave having built something real — and learned patterns you can reuse immediately.
Frequently asked questions
What are the team sizes?
Teams of 1-4 builders. Solo builders are welcome! You can arrive with an idea or form one on the spot.
What technologies will I use?
You'll be building with FunctionGemma for local execution, Cactus Compute as the runtime, and Gemini APIs for cloud fallback. The goal is to create hybrid systems that intelligently decide where computation happens.
Is this hackathon curated?
Yes. This hackathon is curated. Attendees are actively building AI systems in production or near-production environments. You'll be working alongside senior software engineers, technical founders, ML/infra engineers, and researchers translating ideas into products.
Can I participate remotely?
Yes! There's an online/remote option available. You can join from anywhere in the world.
How do I register?
Space is limited to 150 attendees per city, and registration is reviewed to maintain a high-signal room. Click the "Register now" button above to request to join.
What are the prizes?
Prizes and recognition details will be announced on-site. Top teams will receive exposure across the AI Tinkerers network and direct feedback from DeepMind and Cactus Compute teams.
Ready to build the future of local-first AI?
Join engineers, founders, and researchers in building agentic systems that push inference closer to the user without giving up access to frontier models when needed.
Space is limited to 150 attendees per city • Registration requires approval