Oprina is an AI-powered conversational agent with real-time avatar streaming, featuring multimodal Gemini 2.0 Flash integration, Gmail/Calendar automation, voice controls, and enterprise-grade deployment on Google Cloud Vertex AI.
<div align="Center"> # Oprina: Conversational AI Avatar Assistant (It's the first one of its kind) </div>  ## Overview Oprina is a revolutionary voice-powered AI assistant that combines conversational intelligence with interactive avatar technology. Through natural voice commands and real-time avatar interactions, Oprina transforms how you manage your digital life—making email management, calendar scheduling, and productivity tasks as simple as having a conversation with a trusted assistant. Oprina's comprehensive platform features HeyGen streaming avatars for lifelike interactions, seamless Gmail and Google Calendar integration, intelligent voice processing with speech-to-text and text-to-speech capabilities, Google ADK-powered multi-agent architecture with specialized email and calendar agents, and enterprise-grade user authentication and session management. These technologies work together to create an immersive, voice-first experience that makes AI assistance feel natural and intuitive! <div align="center"> <table border="0"> <tr> <td> <img src="docs/images/adk_logo.png" alt="Google Agent Development Kit" width="300"/> </td> <td style="vertical-align: middle; padding-left: 20px;"> <h2><strong>Built for the Agent Development Kit Hackathon with Google Cloud</strong></h2> </td> </tr> </table> </div> </div> *** ## See it in action [Oprina Demo](https://github.com/user-attachments/assets/542a9d0a-b062-4f90-9d13-94cb3d4cf45c) Go to https://www.oprinaai.com to see Oprina live. ## Table of Contents - [Oprina Architecture](#oprina-architecture) - [Backend API](#backend-api) - [Frontend](#frontend) - [Oprina Agent](#oprina-agent) - [Vertex Deployment](#vertex-deployment) - [Supabase Database](#supabase-database) - [Run Locally / Self-Hosting](#run-locally--self-hosting) - [Acknowledgements](#acknowledgements) - [License](#license) ## Oprina Architecture ![Architecture Diagram](docs/images/Oprina_A
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.