A finished research run on an example topic, shown in full — the findings, the sources behind them and the product versions are all the run's own output, except that a product name may have been changed where it matched an existing brand.
A bot-free background capture app covering video calls, in-person conversations, and phone calls in a single local pipeline, replacing the need to juggle separate capture modes for each context.
01
What to build
MVP
A macOS menu-bar app that captures system/mic audio regardless of source (Zoom, in-person, phone via AirPlay/Bluetooth routing), auto-tags the context, and runs local transcription and diarization on all of it in one unified log.
Why it can be better
Otter splits bot, bot-free, and mobile into separate modes, and Hyprnote is scoped to in-person only; no tool spans all capture contexts in one continuous local history as this does.
Revenue model
Monthly subscription for the desktop+mobile bundle, paid by frequent business travelers and salespeople who capture across many contexts.
Target user
Field sales reps, recruiters, and traveling executives who take meetings across video, phone, and in-person settings.
02
Context
The opportunity this answers
Build a local-first meeting-memory layer for professionals that unifies transcripts from any notetaker or capture mode into one private, searchable history.
Why now
A wave of open-source local-first notetakers built on Rust/Swift/Tauri has already proven demand for on-device processing, with diarization and Whisper models now standard, high-download building blocks anyone can bundle, while search interest for generic 'AI meeting notes' has plateaued — signaling the crowded cloud tier is saturated even as privacy-driven local alternatives keep multiplying, and none of them yet unify capture contexts, ingest rival platforms' exports, or sync back out privately.
