1st Place
CrossBeam
CrossBeam tackles California's ADU permit crisis.
legalvisionagents
Mike Brown
AI lab hackathons, 2025 to now
What got built, and what won.
Every submission from hackathons run by Anthropic, OpenAI, Google, Meta and the other big labs, with the winners marked and the code linked.
- projects
- 31,980
- hackathons
- 93
- award winners
- 585
- inferred from GitHub
- 433
Grand Prize
Globot
Multi-Agents. 2M-token compliance analysis. Satellite imagery risk detection. Globot turns sudden supply chain chaos into confident decisions in 60 seconds.
agentsvisionfinance
Victor Orion, Everett Deng, Molling Ma
1st Place
Project
Project: GeminiSpace Track: Gemini in Hard Tech(Option 2) The Problem: Building environmental maps for mobile robots in factories using traditional SLAM is time-consuming, rigid, and computationally expensive.
robotics/hardwarevision
Max Chang
Overall Grand Prize
MLB Pitcher Mechanics Scorecard
Should the manager pull the pitcher? Let's find out. With machine learning and computer vision we evaluate each pitch to see if a pitcher is ready to be pulled!
visionscience
Jake DiBatttista
1st Place
SafeHome Inventory
SafeHome Inventory uses ExecuTorch and Qualcomm's Hexagon NPU to help disaster victims document belongings for insurance claims.
visionproductivity
Yves Hughes
1st Place
blartclaw
building AI surveillance agents for security in a city setting.
securityvisionagents
Aiden Cohen, Kris Diallo, Brendan Fay
Grafana Labs - 1st Place
The Media Customs
The Media Customs clears your commercial for markets before it airs. A Google Agent watches it with you, judges it against each country's law, cites the statute, and re-renders the shots that fail.
legalvision
IBM - 1st Place
Eyeline — Autonomous On-Set Continuity Copilot
Autonomous multimodal continuity copilot for film script supervisors: catches prop, wardrobe, and blocking breaks in the 2-minute on-set window, backed by Gemini 3.8 Flash adjudication and Veo 3.1.
visionagents
Clickhouse - 1st Place
THE GATE
Drop a day's footage in. It finds what coverage you're missing, works out if there's time to get it, and tells you what each answer costs.
productivityvision
mohsen shoraki
1st Place
HomeReady
HomeReady - verify the home before discharge.
healthvision
1st Place
AdSuperSense
AdSuperSense: The Next Generation of YouTube AdSense Problem: Standard mid-roll ads break video flow, causing viewer frustration and churn.
visioncreative/music
Sacha Morin, Tom Gernez, Barnabe Gauquelin
1st Place
food-fight-robots
This game transforms food from your photo folder into robots and fights.
visioncreative/music
Daishi Suzuki
1st Place
TryOnAI
TryOnAI is a universal virtual try-on shopping assistant that lets you chat in any language, browse any e-commerce website in the world, and instantly see yourself wearing any product directly on the website using AI-pow
visionagents
Aniket Khandelwal
Fivetran Challenge: First Place
Alzora
Empowering families with AI-driven Alzheimer’s care
healthvision
Aishwarya Nathani, Nikhil Mankani
MongoDB Track: First Place
Google Fridge
Your AI sous chef that never forgets what's in your fridge - tracking expiration dates, suggesting recipes, and ensuring nothing goes to waste.
visionproductivity
ritz hack, pro tag
2nd Place
Alexis Chapellier
Every year, 50 million tons of electronics become waste — not because they can't be repaired, but because board-level expertise is locked in a few hands.
repair/tradesvisionagents
Alexis Chapellier
2nd Place
Edit Anything
Edit Anything is an interactive tool that lets users seamlessly edit images by selecting text directly on the image and editing it in-place.
visioncreative/music
David Ferris, Audrey Choy, Harsh Patel
Second Place
Aegis: Autonomous Multi-Agent Crisis Command
An autonomous multi-agent command center that prevents 911 collapse by triaging thousands of distress signals instantly using Google Gemini 3.
agentsvision
Danish Mansoori
2nd Place
SkyStudio
SkyStudio: AI-Powered Autonomous Drone Volumetric Sports Capture Traditional sports broadcasting is constrained by fixed cameras and static viewpoints.
robotics/hardwarevision
Rohan R, Mrunmayee Rane
2nd Place
ForenSight AI
ForenSight AI is a multimodal “AI detective” that lets you upload scene photos, videos, audio clips, and witness statements - and instantly generates a unified, AI-reasoned reconstruction of what likely happened.
legalvision
Dhruv Jena, Aadhith Rajinikanth, Rohan Dash +1
2nd Place
Upbeat
Upbeat – AI Music Tutor for Everyone Upbeat - Accessible Music Education For All An AI-powered music learning platform that makes music education accessible to everyone, anywhere, anytime with a camera and internet.
educationvisioncreative/music
Divya Mahajan, Achin Gupta, Param Shah
2nd Place
Sim Sketch Artist
Sim Sketch Artist turns your selfie into a portrait drawn by a robot in simulation.
robotics/hardwarevision
Kazybek Khairulla
2nd Place
ShareLock
ShareLock is an AI-assisted reconstruction tool that helps turn fragmented witness memories into visual leads.
securityvision
Max Neuwinger, Dalia Shaaban, Michal Tesnar
2nd Place
Counterfactual Worlds
I shipped Counterfactual Worlds, a public web application that uses GPT-6 Astra to turn readings and museum objects into interactive, teacher-guided investigations.
educationvision
2nd Place
Homebuddy
GPT-6 Astra interior designer and home furniture curator.
visionproductivity
Alex Reibman, Vibhu Sapra
IBM - 2nd Place
Shadow Cut
"Multitasking is stretched to the limit" — Forbes. Shadow Cut tracks continuity in live pixels on set with Gemini & IBM, alerting directors before wrap to stop $50k reshoots.
visionagents
Patrice Deloffre-Zachelin
Replit - 2nd Place
FrameKind
An accessibility review agent for film editors. Find missing sound captions, rushed dialogue and timing errors, review each proposed repair against the picture, then export a better caption file.
accessibilityvision
2nd Place
Aniket
Upload a real government construction blueprint, ask any element a question, watch it rebuild as a measurable 3D model, and run a pipeline of five AI agents that reads it, measures it, prices it in ₹ from live Indian rat
financevisionagents
Aniket Singh
2nd Place
Sky Guardian
Our technology has reached the point where society needs to stop putting human lives at risk and start leveraging the tools around us.
robotics/hardwarevisionvoice
Armin Foroughi, Nicolas Dos Santos, Alex Battikha +1
2nd Place
ACN-AICenter
デザインの自律レビューサイクル構築
productivityvision
sho akahoshi
2nd Place
Enginuity
Enginuity is an AI-powered parametric CAD application that lets users create 3D solid models through natural language and engineering drawings — instead of manually operating traditional CAD software.
dev toolsvision
Rohith Raghunathan Nair
2nd Place
Problem
Problem: Singapore has bad pedestrians and ever worse drivers.
visionagents
Fong Kai JIe, adore blvnk
2nd Place
Memento
Memento: Voice-Enabled Memory Care Assistant Memento helps individuals with memory loss maintain daily routines through empathetic voice interaction and visual monitoring.
healthvoicevision
Christoph Albrecht, Tanvi Bhardwaj, Vedaant Jain
2nd Place
atelierAI
**NOTE: submitting the project again because of an error in loom video** Our project enables rapid prototyping in fashion design by turning a simple 2D sketch into a fully interactive and visual garment prototype in minu
creative/musicvision
Safinaz Elhadary, Jahnavi Kanukuntla
3rd Place
Custom Universe
A realtime synthetic-data engine for world models.
creative/musicvision
Jake Stevens, Mauricio Pereira
Third Place
Netra: Empowering the Visually Impaired
Restoring independence through AI. Netra provides the visually impaired with a high-speed vision system that reads text, recognizes faces, and describes surroundings in real-time.
accessibilityvision
Amita Mantri
3rd Place
VibeCheck
**VibeCheck** — a UI/UX research agent that automatically audits any product's onboarding experience.
dev toolsvision
Chloe Zhu, Wenhan Ding, Yifan Miao
3rd Place
Archon
Archon is a computer using agent that can control your computer from prompt instructions.
agentsvision
Surya Dantuluri
Clickhouse - 3rd Place
Locaish
The location scout you can send anywhere.
visionagents
Joshua Philip, GremzGit Dhillon
3rd Place
Lattice
Simulation and prediction engine for game physics !!
sciencevision
Richard Rex
Confluent Challenge: Third Place
Woodpecker AI - Finds Hidden Hotspots in Power Lines
Power line failures spark billions in damage.Woodpecker AI, like a woodpecker spotting hidden hotspots via drone thermal streams on Confluent & Google Vertex AI—slashing risks & preventing disasters.
visionrobotics/hardware
Devesh Pandey
3rd Place
Wayfinder
Wayfinder helps patients and visitors find their way around hospitals using their phone camera.
accessibilityvision
Will Halfpenny, Celso Milne, Souradip Mookerjee
3rd Place
crIA - Enrico, Luiz e Marcela
Criação de identidade de marca e publicações para redes sociais para pequenos empreendedores
productivityvision
Enrico Tucunduva
Grafana Labs - 3rd Place
Shot Clock
A crew of Gemini agents watches a VFX render farm in Grafana, works out which shots miss the delivery date, proves why, looks at the frame, and prices it.
productivityvision
3rd Place
Ansr
Ansr is an AI voice host for restaurants that answers every phone call (especially during peak hours), taking orders, making reservations, and answering questions so staff can focus on the guests already there.
voiceproductivityvision
Riddhima Medatwal
3rd Place
seakkx
Most housing decisions today are made from flat brochures and static floor plans — documents that can't communicate perspective, sunlight loss, or how neighbouring towers affect your daily view.
visionproductivity
Sean Yap, kaelan wan, Kai Xun Juay
3rd Place
PrompDojo
PrompDojo is a real-time multiplayer prompt battle where Gemini runs the entire game loop.
creative/musicvision
Haruki Yajima, Shuntaro Tokuda
3rd Place
Chess Commentary AI
Chess Commentary AI is a real-time AI-powered chess commentator that uses Google Gemini Flash to watch your screen and provide exciting play-by-play commentary.
visionvoice
Atharva Walawalkar, Shreyas Yadav, Yuvraj Gupta
3rd Place
MODO
AI Automation workflow powered by visual and audio Will put demo vid in github readme, youtube not letting me upload
agentsvision
Trung Tran
Third Place
AyuSight AI | AI EHR | Making doctors type no more
AyuSight: AI-driven layer linking any EHR, patient app for uploads, and doctor dashboard with unified, visual history—IOP, diabetes, imaging—solving typing, fragmentation, and insight gaps.
healthvision
Om Surve, Vrindar Kelkar, Om Surve +1
Finalist+1
rhmoller
A kid raises a hand to the webcam and a puppet comes to life — mouth, eyes, and gestures driven by their fingers via MediaPipe.
creative/musicvisionvoice
Rene Hangstrup Moeller
"Keep Thinking" Prize+1
TARA
Africa needs billions annually in transport infrastructure but most projects fail at feasibility.
visionfinance
Kyeyune Kazibwe
Best Multimodal AI Application - Web Application
Pet Shelter App
Helping under-resourced shelters find forever homes for more pets, powered by free, private, client-side AI.
productivityvision
Luis Aviles
Most Helpful - Chrome Extension
Nutshell: Hands-Free Web Access for Everyone
Empowers users with motor disabilities to browse the web completely hands-free using just their head and mouth movements, powered by Chrome's private, on-device AI.
accessibilityvision
Han Wei Tan
Best of Live Agents
drone-copilot
Voice-controlled drone copilot powered by Gemini Live API and Google Cloud Run
robotics/hardwarevoicevision
Bryen Param
Best Innovation & Thought Leadership
Rayan Memory
Point your camera at life. Rayan builds a 3D palace from everything you see and hear, rooms you can walk through, memories you can talk to. Your AI that remembers, so you don't have to.
educationvoicevision
Yusuf Elnady
Best Overall Hack
Kel: The AI agent that lives in your computer.
Kel sees your screen in real-time, and is always ready to help — just press Ctrl + K to start chatting!
productivityvision
Manu Anish
Winners
SixthSense: Haptic Vision for the Blind
An affordable wearable that turns a phone's camera into directional belt buzzes, guiding blind and low-vision users around obstacles fully on-device with no internet, at a fraction of the cost of the smart canes and glasses people are priced out of.
accessibilityvisionrobotics/hardware
sixthsense
Honorable Mentions
Relay — Real-Time Voice & Vision Lab Tutor for Electronics
Relay watches your breadboard through your webcam and talks you through building circuits in real time. It sees wiring, catches errors, generates code, and turns builds into 3D digital twins.
educationvisionvoice
Faith Ogundimu
Honorable Mentions
VibeCat
Your proactive desktop companion. VibeCat watches your screen via Gemini Live API, suggests actions before you ask, and executes with self-healing navigation. Built with GenAI SDK + ADK on Cloud Run.
agentsvision
michael chang, Sejun Kim