Mesh
An AI assistant that takes in voice notes, stores information about people you've met, brings up information during meetings, incrementally adds new faces to the detection based on who is present, gives you reminders abo
Core trick
Face embeddings enroll new participants per meeting, while Gemini transcribes speech into action items and translations.
Description
An AI assistant that takes in voice notes, stores information about people you've met, brings up information during meetings, incrementally adds new faces to the detection based on who is present, gives you reminders about previous conversations, and sends action items and summaries after meetings end. It also does live translation, live facial detection, live voice analysis, and has a self-hosted conference calling mechanism and a large backend database to collect information about your network, as well as finds relevant agents in the fetch.ai agentverse through ASI
README excerpt
# Google Gemini Hackathon - AI Meeting Assistant An intelligent meeting assistant powered by Google Gemini AI, featuring real-time transcription, translation, action item extraction, and agent recommendations. ## 🚀 Features - **Real-time Transcription**: Live speech-to-text with Gemini AI - **Multi-language Translation**: Translate transcripts to 11+ languages using Gemini - **Action Item Extraction**: Automatically detect and track action items and decisions - **Face Recognition**: Identify meeting participants using face-api.js - **Agent Recommendations**: Get AI agent suggestions using ASI:One and AgentVerse - **Meeting Intelligence**: Export summaries, email reports, and copy to clipboard - **Telegram Integration**: Receive meeting notifications and summaries ## 📋 Prerequisites - **Node.js** 18+ and **pnpm** (or npm) - **Python** 3.8+ (for Agent Recommender service) - **PostgreSQL** database - **Google Gemini API Key** ([Get one here](https://ai.google.dev/)) - **Clerk Account** for authentication ([Sign up](https://clerk.com/)) - **Oracle Database** (optional, for Agent Recommender) ## 🛠️ Installation ### 1. Clone the Repository ```bash git clone <repository-url> cd google-gemini-hackathon ``` ### 2. Install Frontend Dependencies ```bash pnpm install # or npm install ``` ### 3. Install Agent Recommender Dependencies ```bash cd agent_recommender pip install -r requirements.txt # or python -m pip install -r requirements.txt cd .. ``` ### 4. Set Up Environment