What problem does it solve? Attending and documenting Google Meet calls manually is time-consuming, and automating meeting participation requires fragile browser automation, caption scraping, and audio routing that most agents cannot handle on their own. ## Core Features & Use Cases - Automated Meeting Transcription: A headless Chromium bot joins a Meet URL, enables live captions, and scrapes them into a timestamped transcript file. - Realtime In-Call Speech: In realtime mode, the agent speaks into the meeting through OpenAI Realtime, with audio routed into Chrome's microphone via a PulseAudio null-sink (Linux) or BlackHole (macOS), including best-effort barge-in when humans interrupt. - Remote Node Hosts: Run the bot on a separate machine (e.g., a Mac with a signed-in Chrome) while the gateway runs on a headless Linux box, using bearer-token authenticated WebSocket RPC. - Use Case: Ask the agent to sit in on your standup, take notes, and afterwards summarize the transcript and send follow-up messages or file action items using its regular tools. ## Quick Start Ask the agent to join your Google Meet link and take notes, for example: "join my Meet at https://meet.google.com/abc-defg-hij and summarize it afterwards."
