AI lab hackathons, 2025 to now
Every submission from hackathons run by Anthropic, OpenAI, Google, Meta and the other big labs, with the winners marked and the code linked.
A voice-directed surgical co-pilot for robotic surgery. Surgeons can speak naturally & instantly receive answers, live data on display, and real-time visual assistance - all without breaking scrub.
Aditya Shukla
Voice-controlled drone copilot powered by Gemini Live API and Google Cloud Run
Bryen Param
The Intelligent Desktop Agent for macOS.
Enaiho Uwas Paul, Aman Kumar Sah
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.
Yusuf Elnady
Transforming fragmented family history into living, breathing, multimodal stories.
Jeremiah Somoine
A voice-first AI companion that holds uncertainty instead of solving it. Built on Gemini 2.5 Flash Native Audio with a governed calibration pipeline that learns from every conversation.
Matthew Keats
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.
Faith Ogundimu
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.
michael chang, Sejun Kim
Sit back and relax while our agent help find the right fit
Nikhil Lohar, Siddhant Panday, Vishal Parekh +1
Wand turns the web into something you can talk to and point at. It’s a live AI agent that sees your screen and acts in real time as you speak and point — no typing, no mouse.
AI-powered road hazard detection for Pune — citizens report via video or voice using Gemini Live API, while PMC officers manage hazards through an AI chat dashboard on Google Cloud.
Ekaette is a configurable AI voice and messaging assistant for customer-facing businesses across multiple industries.
Bassey John
A Chrome extension that combines real-time voice AI companions with autonomous browser automation powered by Gemini Live API.
Preetham Shyam
Four AI personas interview you in real-time voice to reveal the gap between who you think you are and how the world actually sees you.
Aditya Pimpalkar, Diksha Sahare
Noor uses Gemini vision to see web pages like a human, letting blind users navigate any website through natural voice conversation, no accessibility markup required.
aliahmedd24 Ibrahim
AR-powered homework help that sees what you see, and helps you see what you don't see.
Linwei Zhang, Jie Kai Tao
Civic Issue Resolving Agent- The Intelligence Behind A Better World
Nibunavarshni Nibunavarshni.S
Real-time AI piano coach powered by Gemini Live API. Play your MIDI keyboard, talk to the AI, and get coached through voice, MIDI data, and hand tracking ? all at once.
Jay Inoue
Call the past. Students phone historical figures through Gemini Live API — real-time voice, natural interruption, tool-driven choices. No quizzes. No scripts. Just conversation.
Quoc Huy Ngo, David Vogel
Food anxiety? Not anymore. Our multimodal AI agent scans food items and products via camera or voice to instantly flag allergens and dietary risks, ensuring you dine with confidence.
Sidharth Sehgal, shivi saxena
Your smart coach for study session!
Kush Patel, Devanshu Pandya, Yogi Patel
Most people leave the hospital feeling lost. Mend is the cure. She sees your charts, hears your voice, and guides you home with magic. It’s not an app; it’s a companion for your life.
Sandeep Wadhwa
PAARTH is an AI-powered Bhagavad Gita recitation tutor that listens to users chant verses, evaluates pronunciation using Gemini, and responds with real-time guru-style guidance and meaning.
Spoorthi Ullal
Personal training is effective, but expensive. Fitness apps are convenient, but passive. We built a live AI fitness coach that gives people real-time feedback while they work out on their own.
Rishik Panjugala
A platform that solves information overload by transforming a daily queue of articles, tweets, and YouTube transcripts into a cohesive, high-fidelity musical digest.
Brian Har
Don't just read research—watch it think technically build.
Sania Latif
Phage: Gives your phone(android) the vision to see the world around it, a voice to speak, and the brain to act accordingly. How about that?
RUSAGUSA Jean Felix
Voice-first AI cashier for small businesses that talks, listens, and handles receipts, invoices, and sales actions in real time.
Dev Femi Badmus
Live Agent Analysis. Your AI copilot that identifies equipment, reads labels, checks recalls, and spots defects — in real-time.
An agent that does a simple engineering workflow with Gemini
Louis Mensah, Emmanuel Mensah, George Mills
MusAI ends the "cognitive friction" of music practice. A sovereign Gemini 2.5 Live ecosystem that replaces fragmented tools with real-time, multimodal mentorship for mastery. Inspiration via data.
Der Tab
Every agent I've seen makes the human do the work. You prompt carefully, wait, correct it, prompt again. I built Rio because I wanted to flip that completely.
Gowshik S
Gentle tech guidance, one step at a time.
wenn00 Lee, hjcIoog Huang
A multimodal AI content detection system that analyses text, images, audio, and video and proactively predicts what misinformation will emerge from official announcements before it spreads.
lohjo Ray
The first AI agent that crawls your SaaS application to generate high-precision explainer videos for every page, automatically.
addads agency
A multimodal, productivity agent that sees your distractions, talks back, and takes action to keep you focused.
Nicolas Biakou
Studio One: A multimodal AI movie studio. from script, design, and animate films in one UI. Gemini 3 keeps character consistency from the first frame to the final export.
Mohamed Abdrabou
ai guided tours to learn any software and in any language with help of AI
Vaibhav Maheshwari, kaivan Doshi
Five AI agents run a full conference experience — from personalized invitations to live voice travel booking to an interactive keynote — all powered by Gemini Live API, ADK, and Google Cloud
hmshimanyula1995 Shimanyula
An AI dive buddy housed in a waterproof smartphone case that uses the camera and microphone to keep divers safe, oriented, and educated in real-time.
Alex Holderness, Stanislav Karzhev, Inaya
You speak in thoughts — AI needs structure. Kinapse restructures your voice into precise, AI-ready text across any app, and teaches you to prompt better with every interaction.
Alban Li, Hins Hu
Real-time voice + vision AI co-pilot for field technicians. Sees equipment through your camera, searches manuals instantly, and speaks expert diagnoses — powered by Gemini Live on Google Cloud.
Suman Sarmah, ARJUN PRATAP DAS
Trace of Ink is an AI book where choices build new worlds. It makes art as you read and remembers every path. You direct an infinite story tree.
Bilal Saim
AI patrol partner that sees through your phone camera, speaks proactively, detects anomalies with ESP32 beacons, builds a real-time 3D building model, and auto-generates duty reports.
A multimodal AI debate opponent that fact-checks your arguments and corrects your body language in real-time.
Hamza El Rachdi, Ahmad Zeid
A real-time voice AI tutor that preserves Ghomala', a vulnerable Cameroonian language, using Gemini Live API and Vertex AI SFT
Parfait Ben-oni TEDOM TEDOM
Prometheus is the solar advisor every homeowner wishes they had - it sees your roof, bill, shows you what panels will look like on your house, and sends the installer quotes. All in one conversation.
Umang Raizada, Sai Praneeth Reddy Chana Reddy
Northstack is your all-in-one AI OS for founders, packing a full squad for business, execution, and personal growth into one fast, high-performance command center.
Govind Waghmare
Navigating the web shouldn’t be a barrier for blind users. My project leverage agents to make websites fully understandable: agents type, click buttons, and explain what is on the page.
Rachel Chen
Complete lab automation accelerating discovery is the dream of every researcher. Miko now brings it so closer than ever. Speak to experiment, observe, and optimize. From operator to conductor.
Speak anywhere.Act everywhere.One AI brain. Every device. Infinite capabilities. Connect your entire digital life with a single, intelligent agent that spans across web, mobile, and smart glasses.
Omanand Swami, Pratik Patil, Harsh Kale
A multimodal cinematic engine that kills the editing timeline. Type a vibe or upload memories, and daydream orchestrates Veo, Lyria, and Gemini to generate a flawless, beat-synced reel instantly.
Aashir Javed
Just point your camera at your ingredients and talk. FreshCheck identifies items, tracks expiry dates, and suggests recipes — all hands-free with Gemini Live API.
book class
An AI tutor that talks back. Socratica uses live voice and Socratic questioning to coach you through lessons, presentations, interviews, and written evaluations, personalized to you.
Alex Imbrea, maria secara, Mara Teodorescu
Talk to Scout — instant AI-powered brand intelligence, hands-free Voice-first competitive research Your AI brand analyst, activated by voice
Tejus Dinesh
Complex concepts made easy with interesting visuals.
Ebube Life
Provide a short tagline for the project. You can change this later.
Francis Kioko
SHIK Live gives real-time AI something no current agent has: a persistent self.
Susan Kingsley, James Kingsley
A voice-based restaurant bouncer simulator where you talk with customers and decide who gets in, balancing fairness, rules, and the restaurant’s capacity.
Nahuel Bigurrarena, Valentín Colato
AI design co-pilot that connects to Figma, understands a team's design system, and delivers expert-grounded UX critique
Abdullah Ibn Mahdi Abtahi