3 front-ends over one core
$0 running cost
0 audio bytes uploaded

Overview

Cloud notetakers work by uploading your meeting. That is a reasonable engineering choice and a poor privacy one, and it means the tool only works where a bot can be invited.

Meeting Bot captures the audio already playing on the Mac (Zoom, Meet, Teams, FaceTime, or a browser tab), so it needs no meeting-platform integration and works with any of them. Whisper transcribes locally. The only optional network call sends the finished transcript text for summarization, and that endpoint can point at a local model instead.

What I built

Three front-ends, one engine

One core drives a native macOS SwiftUI app, a Chrome extension, and a CLI, with an iOS companion that records from the microphone on-device. Keeping the engine separate from the surfaces is what makes three front-ends cheap to maintain: each is a thin driver over the same record, transcribe, summarize and export pipeline.

Results

Stack

Next: Agent Certifier
Sixty static-analysis tests that grade an AI agent codebase without running it
All projects
The full set, thirteen projects across agents, vision, and full-stack