Devpost · Google · 2026-02-16 to 2026-03-16
Public gallery: every submissionEvent page ↗
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
Test
Nadeem Mohammed Shajahan, Thomas Kuruvila
A "friend" that you need when you following tutorials.
Julio Bellano, Benedict Estefan
SlopSlayer: A real-time vibe check that roasts deepfakes and spots AI slop before it spreads.
Benaih Galavu
A voice-first AI tutor for children who lack access to a teacher. Speaks their language. Sees through the camera. Remembers every child. No typing. No English. Just talk.
Pranjal Madan
Short screen-sharing session to observe your work and understand processes. Turn your expertise into reusable knowledge and workflows to automate tasks and leverage AI daily while you focus on work.
Yafa Yafa, Luc Aractingi
An AI-powered interactive storyteller that helps children read, create, and learn through voice and imagination.
Tarang Chandrasekharan Nair, Parixit Sanghani, Vijay Vanapalli
Aegis Caregiver powered by Gemini Live is a 24/7 AI "Memory Prosthetic" that transforms Dementia care from reactive to proactive. We’ve created an 'Always-On' layer of intelligence.
ritika Ritika Mahajan, Menomi Gamage
Elsie is a real-time AI that reads your lab report, watches grocery shelves through your camera, and tells you what to grab, as naturally as asking a friend standing next to you.
priyanka nayyar
A real-time AI math tutor powered by Gemini Live API , voice-first, interruptible, with step-by-step explanations, live transcription, and camera input for problem solving.
Mohamed Ghareeb
Your silent edge in every negotiation.
Arnav Nayak, Amvi Dwivedi
Mimesis studies your brand, builds the strategy, and generates images and video with your team live, so you explore more directions and pitch commercial concepts to the client the same day.
Yanis LAZREQ
Your habits deserve more than a checklist. Talk to an AI partner who sees, listens, remembers, and holds you accountable — every single day. Accountability in your pocket.
Jennie Littleton
An AI agent that watches your screen, plans the next step, and executes it - across any app, without APIs or scripts. Powered by Gemini vision and Google Cloud.
Hossain Anas, Abrar Fahim
Corides.ai leverages live AI to connect drivers and riders in real time, creating efficient carpools that save fuel, time, and money.
Faisal Ismail
HadithiAI is an AI storytelling application that preserves and shares African culture through interactive voice stories, riddles, and intelligent AI agents.
Abraham Imani, Georges Byona
The web, navigated by voice. Any site. Any page. Zero barriers.
E Kolawole
Your personal, voice-driven AI Companion. It watches your screen and takes control of your apps to accomplish complex, multi-step tasks across your entire computer.
Kalisetti Dheeraj Babu
AI storyteller that streams illustrated, narrated storybooks in real time by orchestrating Gemini, Imagen, and TTS as a single creative director.
Qiang Wang, YIXUAN Wu
Review room live turns speech and visual evidence into a real time structured review summary, helping professionals ask smarter questions, spot issues faster and leave every session fully organized.
Naveen Chatlapalli
An autonomous AI QA agent that sees your UI, reasons with Gemini, and reports what's broken — before your users do.
Vignesh SP, Ramya Shantha
CreatorPilot is an AI agent that turns trending news into fully rendered YT-ready videos with captions, metadata, and publishing strategies-automating the entire creator workflow from idea to upload.
Priyam Singhal
A real-time voice AI hidden inside a musician's album campaign. You dial in. She picks up. She knows the story. She remembers you. Built with Gemini Live API in one day.
Cameron Cloman
Once upon a time, AI wrote soulless children's books. FairyDraw fixes that. We supercharge the human touch, fusing AI and creativity so anyone can craft stories you'll actually read to your kids.
Lilian Froutan, Marvin Schmidt
Sanak transforms stories into a living tree. Through real-time voice conversation, our AI biographer listens to your memories and autonomously sketches a vivid, explorable genealogy graph.
Giga Hidjrika Aura Adkhy
Your personal AI tutor — pick a study method, pick a persona, and learn through live conversation grounded in your material.
Peter Williams
Field Mechanic is a real-time, multimodal AI agent that guides users step-by-step through car repairs (e.g., alternator swap, battery replacement).
Muhammed Ibrahim
Agents shouldn't read raw HTML. Powered by agentic-research/mache, X-Ray uses Gemini's vision to project any webpage into a semantic filesystem. Navigate the web with your voice - no guessing.
James Gardner
Basketball AI Ref, an agent-powered multi-angle referee. This is a Live Review Room: agents analyze various angles of a single play to determine a verdict to the user as an interruptible referee.
Skyler C
A child calls 911: "mommy isn't moving." Three callers, three AI agents, one verified truth. Nexus911 — autonomous dispatch with real-time hallucination verification.
Dennis Sharon Cheruvathoor Shaj
Real-time voice AI that catches life-threatening drug-gene interactions at the bedside.
Layal Yasin
97% of the web is invisible to screen readers. Apollos uses Gemini Vision to navigate it by sight — the way a sighted person would.
Aegis is a self-healing cyber engine bridging Windows logs to Gemini Live. It offers sub-200ms multimodal threat reasoning and Firestore-backed recovery for a resilient, autonomous SOC sentinel.
Rambabu Katkuri
A hands-free, multimodal AI cooking assistant that watches, listens, and guides you step-by-step so you never have to touch a screen with messy hands.
Ibrahim Kako, Michael Salami, Rehan Ananth
Fluently: The AI speech coach that hears, sees, and corrects you in real-time.
Rayirth Saharan
AI Director’s Box turns sports footage into narrated, cinematic experiences. Using Gemini and Imagen, it adds tactical insight, persona commentary, highlight, and an interactive storybook of the match
praneeth sunkavalli, Mark Fahim
A screen-aware health AI companion that lets you talk to your medical records. Ask questions, navigate the app, and compare results - all by voice, hands-free.
Xavier Flanagan
A Raspberry Pi device for K-12 science. Instead of giving answers, it guides kids through textbooks using Socratic questioning. No tabs, no copy-paste, no distractions — just thinking aloud.
Dingran Dai
Disrupt the AI overlords proclamation day without getting caught. Whisper to other attendees to spread gossip and sow dissent.
Paul Newton
AI agent that reads your receipts, tracks spending patterns, and coaches you on finances
Isha Shetye
Filegraph is a voice-controlled desktop workspace where a Gemini-powered agent sees your UI, navigates files, manipulates canvases, and executes 50+ actions, all through natural conversation.
Trenton Brew
An Integrative Health App to Assist Doctors and Patients.
Phil Gear
Mama AI is your voice-first tutor grounded in your curriculum. Just talk, show your work, and get custom diagrams, animations, and a virtual whiteboard to clear every doubt.
VENU PATTIPATI
We designed a live Electrical Engineering Teaching Agent that can help debug hardware in real time. Using a microcontroller, probe and a camera module, we relayed electrical information to the agent.
Eren Mengeş, jothomas10102 Thomas
AI-powered bilingual storytelling that bridges heritage languages through interactive bedtime stories with watercolor illustrations and narration. Built with Google ADK + Gemini.
Pyae Sone Kyaw
Pathly turns every run into a live, route-aware two-host podcast.
Lucia Du, Elaine QIAN
Predictable AI animation studio for long-form cartoons
Indrek Luts
A Next-Generation, Real-Time, Multimodal Large Language Model-Powered AI Companion and Tour Guide.
Jiaqiao Situ
A private personal coach to help people not only overcome their fear of speaking but also level up their public speaking so that they can be empowered by it and communicate their point of view.
taylor parsons
Kitchen Studio - an AI kitchen copilot that cuts decision fatigue and cooks with you in real time
Osita Miles, Obasi Peace Oluchi
Your AI-powered personal stylist with virtual try-on, blockchain ownership, and social sharing — all in one fashion discovery platform.
Papa Jams
Jarvis for the gym: a live AI coach that sees, speaks, and corrects.
OmniAi: Your perception-first digital life companion.
Celestine Obi
Live agent research navigator for literature overload
Louell Sala, Michael Brenner, Angelie Singh
Solve the AI trust gap. ComplyAct uses Gemini 1.5 Pro to build auditable agents that navigate UIs and halt for human review, ensuring 100% accountability In immutable ledgers.
LiveNotebookLM reimagines Google NotebookLM as a live, voice-first experience. Upload your PDFs or documents, add web sources, and have a natural spoken conversation about them.
Guanqiao Chen, Mike Wang, Terry Mu
CineAI is an AI storytelling engine that turns ideas into coherent cinematic scenes, allowing anyone to create films without the traditional production pipeline.
Mythical Knave
YTB is your real-time AI hypeman and wellness coach. Powered by Gemini, it reads your expressions to proactively deliver pep talks, breathing exercises, and ambient sounds right when you need them.
James Stowe
Hire smarter, faster. Truefit.ai conducts AI-powered interviews, evaluates candidates instantly, and delivers structured reports, so you can focus on decisions, not screening.
Olaniyi George, Joshua Olumoyin, Hill Onyechekwa
TELOS is a Gemini-powered Windows UI navigator that sees the desktop through screenshots, interprets apps with multimodal reasoning, executes actions through UI Automation.
Yashwanth Gathuku
An autonomous multimodal security agent that navigates web UIs, reasons about business logic, and discovers vulnerabilities traditional scanners cannot detect.
Compass: paste a GitHub URL, get an AI that's read your entire codebase — briefs you by voice, watches your screen, and speaks up when you're about to make a mistake.
Ananya Gupta, Akshat Shende
AI creative director that learns how you perform *not just what you say* and co-creates content in your voice.
Brooke Lacey
Witness is a noir crime game where your real room becomes the crime scene. You're the detective. The AI is the witness. Your job is to question it, pressure it, and catch it in a lie.
Krish Verma, Sarath Kumar Dunga, Aniket Swaroop Shrivastava +1
A multimodal AI agent that helps researchers explore diabetes papers through voice, vision, and data.
Tuba Karaca
Roam is an AI tour guide on your phone that identifies landmarks via camera and GPS and gives personalised, multilingual, gamified audio tours to navigate the culture of cities, museums and more.
Ishaan Shah, Anay Shah
S.P.E.C.T.R.E is a cutting-edge, real-time AI assistant designed for developers. It monitors your screen to proactively detect errors, suggest optimizations, and autonomously apply code patches.
Max Prime
Devil’s Advocate is a live voice AI that stress-tests startup ideas through grounded debate, real-time interruption, and post-session reports, so founders can refine weak assumptions fast.
Zaina Qasim, Deji Olaleye, Sean Kraemer +1
A smart personal assistant that helps anyone, anywhere, easily find doctors, book appointments, and manage healthcare without tech confusion.
Mohammad Ashfaqul Hasan, Ahammad Shawki, Ragib Shahrier Bin Kabir
A multimodal Gemini Live agent that uses real-time vision and voice to help users sort waste correctly based on local municipal rules—reducing landfill waste one scan at a time.
Voice-driven AI creative director that learns your brand once and never needs to be told again. Doesn't reference your guidelines. Becomes them.
Kurt Miller
A real-time multimodal AI interviewer that sees, hears, and speaks naturally, with interruption-aware coaching grounded in your target job description.
Jaume Noguera
Conversational Learning!
Pranav Pipariya
TATO is a decentralized resale network. From personal items to retail dead stock, our AI digitizes your inventory so zero-capital brokers can sell it for you. True passive income with zero hassle.
x
Give people with vision loss genuine social access. Have a real conversation about what they're seeing, post to social media, and hear what their friends shared—all through natural voice interaction.
Peiqing Zhang
An intuitive 3D space where you can inspect, diagnose, and directly edit an AI agent's semantic memory — in real time, with your voice.
Yosun Chang, Caramel Corgi
The story was always there.
Diwash Kuskusmiya
The voice layer for enterprise software.
Elman Abiyev
a terminal tool where an AI agent can literally use your computer for you.
Ethar ahmad
Build the product. VividLaunch handles the launch.
AURILIX is a two-way symbolic language interpreter.
Shravani Vanalkar
A Gemini-powered orchestration system that deploys real-time browser agent swarms, with live voice control, memory, and human-in-the-loop safety.
Kevin Doshi
Drop evidence on a canvas. AI finds contradictions, spots gaps, generates cited reports, and reconstructs scenes as video from testimony. Edit by voice.
Larris Xie, Dongha Kim
Give Luna a theme and she paints your story - an interactive visual novel with AI-generated impressionist art, prose, and voice narration, all woven by Gemini's multimodal output on Cloud Run.
Ayan Liger
Stop spending countless hours fixing the flowcharts in your slides, do it in seconds, using your voice!
Christina Stejskalova
A real-time memory preservation agent for families.
Ritish Nedunoori
A action taking interactive Gaussian Slatting 3d avatar that can guide visitors around your website, see what you see, find items you looking for, and act as an overall web site assistant.
Antonios Makro, Goran Jakovljevic
Eyes that never blink. Memory that never fades. A heart that understands how you feel.
Dhruv Arora, Aarya Bajaj
An AI infrastructure audit and intervention tool that uses Gemini 3.1 to prevent "Functional Deafness" and uphold human sovereignty in Industry 5.0.
पुनित मदान
Your restaurant's AI phone staff — answers every call, takes every order.
Yijie Z hu, HikingMia, Jensen Chen
An AI architect you can talk to. Discuss your project idea by voice — Smith generates requirements, architecture diagrams, tasks, and timelines in real-time. From conversation to structured plan.
Shumpei Kobayashi
The first language app that teaches you by dropping you inside a living, voiced, illustrated story — where the only way forward is to speak.
yahya samet, Ghada Eladeb
Your fridge, pantry & recipe book are just a call away!
Asa Schaeffer
The Execution Co-Pilot: Closing the loop on network resilience through agentic UI navigation and policy-bounded circuit remediation.
Using live agent to help user scan invoice, unknown fields are trained on the spot by gemini. these are used for uptraining in document ai. scanned items are all stored on googlesheet
tantk tan
Teacher-student interactivity from home, Senti will plan, generate and walk you through any academic subject you ask for all while seeing your whiteboard live.
Nooredeen Amr
A 3D desktop genie powered by Gemini that sees your screen, understands any UI, and performs tasks across any app on any OS — by voice or text. No APIs, no DOM access. Pure visual understanding.
Md Abu Bokkor
Lovely is a (very!) smart camera for travelers. It's not just taking pictures: it helps you to get to know the world.
Alex Farlander
A layer on top of Google Workspace that connects your apps, screen, and data — where Gemini alone can't reach.
Sanika Sawal, Vishal Sunil Kumar
Agent simulating dental patient encounters to help postgraduate dentists prepare for clinical exams by practicing history taking, patient assessment, diagnosis, consultation, clinical decision-making.
Lamis Hassan, John Hakeem, shams-inflaixus +1
Point your camera at anything, speak naturally, and learn a new language — Luna sees your world, hears your pronunciation, and teaches vocabulary through real-time immersive conversation.
Kumaraswamy Chavvakula
Automate anything. Just show Echo how.
Jason Mun, Andrew Cheung
Vision Homework Tutor is a multimodal AI tutor that solves homework from images or text, giving step-by-step explanations, hints, and multilingual support.
Vivek Muskan
AI-powered real-time scam detection that sees, hears and speaks, protecting everyday people from phishing, fraud and voice cloning scams.
Krishna Modi
LensIQ is a live multimodal exploration agent that turns your phone camera into a conversational guide, seeing what you see, hearing your questions, and answering out loud in real time.
Telli Koroma
ArtMaster AI is a full-stack web application designed to provide real-time, interactive art instruction and feedback using the Gemini Live API.
Arivoli Anbarasu
Stop overpaying online— The Future of smart shopping
Tim Wu, danny dang
prompt to video is a structured animated video plan. our platform understands a user’s idea and generates a full pipeline for video
Zevdun Arjuna
AI-powered Arabic storytelling where children play and the system silently assesses cognitive, linguistic, and social-emotional development — turning every story into an invisible classroom.
Mohammad Saed Haj Ali
Kenya's voice-first electronics store. Talk to TroveVoice — a Gemini Live AI concierge — find products, compare specs, and pay with M-Pesa. No typing required.
SG Kamau
The Multimodal Soul of Bocas del Toro - Simplifying booking a captain or tour in the archipelago
Dorien Van den Abbeele
AI-powered personalized children's storybook generator where your child is the hero — guided by a voice assistant, illustrated with their real face, narrated as an audiobook, all in minutes.
Vinay Guda
A portable, AI/cloud/sensor driven, situation-aware virtual pet. Powered by GCP and Gemini, runs on various hardware platforms including PC, Raspberry Pi, Nvidia Jetson.
Yelena Yu, Shi Yao Liu
A real-time voice AI that uses a mathematical behavioral engine to prioritize sovereign peerhood over subservience.
Nabeera Khan
UISurf lets multimodal agents collaborate to automate tasks that combine web browsing and computer-use workflows from a single prompt
Henry Ruiz
Real-time voice AI agent powered by Gemini Live API that detects options mispricing and delivers actionable trade signals through natural conversation on Web interface, Voice and Whatsapp.
Somesh Dubey
Voidpilot makes Gemini feel alive: talk naturally, get grounded answers, and create images, videos, and ideas in real time. It's not another chatbot, it's your vivid creative co-pilot for every spark!
Nik Anand, sofia Anand
A continuously aware, clinically-grounded AI copilot acting as the user's eyes in the real world and on-screen, built on the Gemini Multimodal Live API.
Olamilekan Adegoke
Reptrainer simulates real buyer objections using Gemini Live, grounds evaluations in your actual product knowledge, and helps teams close with confidence.
Huncho Satchamo
Gemini-powered multimodal storytelling that helps GBV survivors in Kenya recognise abuse through illustrated, narrated awareness stories — because recognition comes before help-seeking.
Naijeria Toweett
Brands need fresh content, but making ads is too slow and costly. AdGen solves this by instantly generating image ads. Tweak designs in an editable canvas, then easily export them as video ads.
Ritik Bompilwar
Live technical collaboration room for humans & agents.
Simon Dunkelman
Live, voice-controlled 3D command center.
Tayyab Khan, Sahil Jayesh Tanna, Kumar Nikunj Sinha
Upload your memories. In minutes, Mémoire generates a fully illustrated, narrated as a graphic novel that you can share with everyone who was there.
Favour Achara
Evaluador de salud en tiempo real. Usa visión y voz para analizar síntomas y etiquetas de fármacos con latencia sub-segundo, ofreciendo una guía preventiva empática y multimodal.
uketdonuts Santamaría
Find inner peace at home. Co-designed with the founder of Ottawa's ChaDynasty tea house, Master Chady uses Gemini Live to guide authentic, calming Gongfu tea ceremonies in your living room.
Tiancheng Chen, Sophia Y
Mom speaks Hindi, wife speaks English. BabelChef uses Gemini Live API to translate their video call in real-time - so Mom can guide her through biryani, spice by spice.
WiseOwlBuys ConsumerApps
Talk to your video. StoryLabs is a Gemini Live agent that hears your intent, sees your editor, and applies edits in real time. Stop editing. Start directing.
Stephanie Ng
A visual live AI instructor at your hands.
Kareem Amr
Helping loved ones navigate with confidence
Patrick Paumier
DeskAgent is a smart desktop assistant that turns natural language commands into real actions on your computer.
Abdullah Khetran, Ahmed Faraz, jahanzaibm29 Jahanzaib
Turn your research database into cinematic live-data stories on a wall display. Visitors scan a QR code and ask an AI companion about any data behind the story.
Housny Mubarok, keii111 zulaikha, DOOM DOOM
Ask Anything. Watch it come alive.
Nippun Sharma
Point your phone at any used car — CarCheck's AI inspector finds hidden damage, flags fraud, and tells you what it's actually worth. In real time.
Aswin Shailajan
Turn your idea into film
A real-time, multimodal AI investor panel for founders to practice pitching.
Emmanuel Etim, Abhishek Gurjar, MAURICE Makafui +1
An AI agent that interacts with elderly customers and teaches them how to leave a review.
Matthew Feroz
Chronos turns any "What if?" question into an immersive alternate history documentary — AI-generated timeline, scene images, voice narration, world map, and cinematic video. Powered by Gemini.
Fiddausi Danjuma
Rena is your AI health companion — log meals, track workouts, and stay on track toward your goals through natural voice conversation, powered by Gemini.
Avinash Gosavi
A live AI companion that sees what children point at, responds with voice, remembers discoveries as treasures, and turns them into personalized stories and play.
Tim Wu, Jiali Xu
Lumi listens to your live conversations, sees your screen, and intervenes at exactly the right moment, a nudge card, a chime, or a voice answer, without breaking social flow.
Khushi Navin Patni
Visual QA Navigator is an AI-powered UI Navigator agent designed for the Gemini Live Agent Challenge that interprets web interfaces visually to detect regressions and automate functional testing.
Ronald Kuseski
A real-time, voice-driven UI navigator that solves the "last-mile" of automation by keeping the human in the loop via live multimodal feedback and visual grounding.
Solomon Nderitu
Our proyect is a AI agent that work as a participant in a google meets session and behaves by a previous given configurable roles, so at the end of your meeting you get a full detail of everything.
Omar Núñez, Richard Quiros, Christopher Jimenez
Janus: a real-time AI companion with AR, image creation and video that sees, hears, talks and plays with your child, then reports to the parents with full session logs, summaries, and safety alerts.
Chaitanya DS Thakur, Christopher Lamers, Matthew Power
Savant Synesthetic Agent is a specialized cognitive partner designed for neurodivergent adults (Late-identified Autism, ADHD, and Synesthesia).
Gabriella Peña Villegas
AI-powered vocal coaching that detects strain and speaks technique cues at every breath point - Powered by Gemini Live.
RedFox485 Ford
Drop any historical document. Get a cinematic documentary back researched, narrated, and illustrated by AI agents you can talk to mid-playback.
EFE ÇELİK, Berkay Aktaş
Sing Chinese songs in ENGLISH. Edutainment across cultures. Build your MV now.
Allard Quek
Turning a Smartphone into Intelligent Eyes for the Visually Impaired
muhammad tariq nazir
Multimodal incident agent for SRE/DevOps: voice, screenshots & logs in one flow. Gemini-powered triage with human-in-the-loop.
armandobecerraro Becerrra, Carlos Suescún
Understand your cat’s intent through sounds and actions, and have real conversations with your kitty.
wudixiaolou guan
Sentinel-911 is a fully agentic AI assistant that instantly answers, prioritizes, and dispatches 911 calls to eliminate delays and save lives.
Pranav Prasanna Venkatesh, Aadi Saraf, Aviv Chatterjee
W(AR) CHESS makes the board come alive. Pieces talk, a Gemini Live narrator hypes the match, and an AI coach helps you improve. With goofy roles and cosmetics, learning chess finally feels fun.
Kunal D Singh, Andrew Hong, Gurraj Singh
Ask a spiritual question by voice. Hear Srila Gurudeva's actual recorded voice answer you — retrieved from real harikatha, not synthesized. As it is.
Amit Bhaskar
An AI agent that sees your crypto chart and delivers instant trade analysis, entry, stop, target and risk calculations.
Om Shukla, Ayush Shukla
AI health companion that records doctor visits, summarizes conversations, analyzes prescriptions via camera, translates languages live, and sends smart medication reminders using past health data.
Bharathi Raja R, Anusha Bandi, kumud kode +1
An AI pair assistant.
Rafael Moraes
"Bridging the gap in dementia care with an AI companion that preserves memories, monitors safety, and keeps families connected."
Jobin Devasia
Navigate and deliver.
Dillon Morais, Smrithi Shera
Pixel Pilot turns words into action. It’s an autonomous desktop agent that sees your screen and clicks, types, installs software, and handles admin prompts: so you get results, not instructions.
Biruk Abza, Yonatan Yishak Yifat, Dagemawi Bekele Negash +1
Beyond the chat box: A real-time, voice-driven AI agent that sees your browser, sees you, hears you, and acts for you.
Kamil Pastwa
Real-time AI veterinary co-pilot that watches livestock through cameras, tracks individual animals, and talks to farmers using natural voice — powered by Gemini Live API and Google ADK.
Aravind V
Describe your system out loud. COMPASS maps every NIST 800-53 control, surfaces compliance gaps, and generates your FedRAMP OSCAL documents — all in one voice conversation, powered by Gemini Live API.
ivproduced Harris, Dr.Trulove
“STARK is a personal AI agent with its own evolving brain that can understand tasks, generate code, learn from interactions, and assist users in real time.”
Balu Thota
Voice+vision AI command center (Gemini Live + ADK) for governing a federated fleet of AI agents via natural conversation, with approval workflows and monitoring on Cloud Run and Firestore.
Sai Sunkara
Gives the visually impaired real-time independence. Powered by Gemini 3.0 Flash, our voice-first AI guide masters grocery trips, document reading, and environmental safety effortlessly.
Lasse Stilvang
Turn a child's drawing into a living story and animated movie using a multimodal AI storytelling agent.
Trish Whetzel
Meet our project—an intelligent, real-time AI Co-Presenter. It sits right on your desktop to act as your ultimate presentation wingman, powered entirely Gemini!
Tran Anh Tuan
The AI Operating System for founders. 8 agents run your engineering, marketing, sales & security 24/7, hold voice meetings, and only ping you when a real decision is needed.
Sidy Mbengue
A live voice-and-vision mobile game where your knowledge grows a district on the map with real-time AI, camera quests, and squad missions.
Amir Lotfy
Zaute is a realtime, 3D AI fashion stylist. Using the Gemini Multimodal Live API and Nano Banana, Zaute provides sub-second voice fashion advice and instantly generates photorealistic virtual try-ons
Mudy Edogun
Osirus AI is the UI for AI — a multi-modal enterprise development platform that unifies chat, search, image, video, and speech into a single interface, powering the services that enable agentic AI.
Tech CTO, Matthew Garrepy, Goyal Seelam +1
Yêyê is my final project to showcase the skills I've picked up during my challenging journey of becoming a certified Google Cloud ML Engineer.
Willinton Triana Cardona
Chefeze is a live cooking copilot that listens, sees pantry and cooking context, and guides users with grounded voice, vision, safety, and budget-aware help in real time.
Rafael Bittencourt, Aline Gonçalves dos Santos
An AI market analyst that sees your trading charts, hears your questions, and talks back with institutional-grade analysis in real-time using Gemini Live API.
Edd Clandestino
ArionTalk lets users talk to any webpage. It listens to the user, understands the page content and images, responds with voice, and scrolls to highlight the exact section it's discussing.
Luis Aviles
An agent that helps advocates create a personalized re-entry plan grounded in the prisoner’s own words and correspondence.
Ashvin Pai
Chatboom is an AI-native messenger that answers calls when you're busy, takes smart notes, saves in calendar, and an in-app Copilot to draft messages and navigate hands-free.
Muhammad Wafa
NIBO was engineered to address a systemic vulnerability in current-generation LLM-driven browser automation: The Latency-Security Gap and the focus of SCAM prevention
Ivann Comiso
Meet Cygnus, the international flight agent you probably didn't know you needed
Alissa Troiano
A live interview expression coach that turns spoken answers into clearer, more confident, professional responses.
Zihao Qi
Socratic Mirror: a real-time multimodal AI coach that listens, watches, and adapts instantly to help you speak, interview, and learn with confidence.
Krishna Karra
A hands-free voice cooking assistant; talk to her while you cook, she remembers your allergies, sets timers, and even watches your pan through the camera.
Stephanie Angulo Alva
Interactive AI Agent guiding the visually impaired through visual environments.
Atakan Nalbant, ömer yılmaz
Appi is an AI-native operating environment where agents and humans can work together through live interaction, native commands, and a lightweight shared runtime
Yafa Yafa
Northstar is an AI web navigator that helps anyone complete tasks across the web, especially when websites are inaccessible or hard to use.
Your personal AI baseball commentator — watch live games with real-time voice commentary and animated reactions, all in one interactive experience.
Hung Yu Hsiao, Ting-Wei Chu
Real-time pharmacogenomic sentinel. Gemini Live listens to doctor consultations, detects drug prescriptions, and triggers a C++23 barge-in alert on critical genetic contraindications in 40ns.
Riyane El Qoqui, lilolilia
AI Creative Director for Kenyan Artisans Soko Studio is a next-generation multimodal agent built for the Gemini Live Agent Challenge
Lewis Sawe
ZeroWait is a voice-powered assistant that tells patients if Dr. Sanchez is running on time and lets them quickly notify the office if they’re delayed.
Osi Nwankwo, Nuriy Gold
A FastAPI + Gemini Live API backend for a browser-based voice assistant that operates across Google Workspace on behalf of the signed-in user.
Daliseiy Oluseye