Kennan
Privacy by architecture

Private, on-device AI for your meetings.

Most real-time meeting tools route your audio through someone else’s server. Kennan doesn’t. Transcription happens on your Mac. The language model can run on your Mac too. If you want a frontier model, you point Kennan at your own API key. Nothing in between.

For macOS. A lifetime license, pay once at launch. We only email when Kennan ships.

What “private” actually means.

Privacy is not a policy promise. It is the shape of the request graph. Below is what leaves your machine, when, and where it goes.

  • On-device transcription.

    Audio capture and speech-to-text run on your Mac. The recording, the diarization, and the transcript live in memory or on local disk. They are not uploaded.

  • Optional local LLM.

    Pick a local model and the entire pipeline is offline. No network calls, no provider in the loop. Yours alone.

  • Bring your own keys.

    Prefer a frontier model? Configure OpenAI, Anthropic, or Gemini with your own API key. Your Mac talks to the provider directly. No relay server.

  • No account. No email.

    There is no signup. Your account is your Mac. We do not need an email to let you use the app you bought.

  • Invisible to the call.

    Kennan does not join the meeting as a bot. The HUD floats on your screen and is excluded from screen-share and screen-recording. The other side sees nothing different.

  • Lifetime license.

    Pay once. Use forever. No subscription, no seat creep, no renewal email three months from now asking you to upgrade tiers.

Read the full privacy architecture

Real-time, in the room.

Kennan listens as the conversation happens and surfaces the next thing to say, in first person, on a HUD only you can see. Built for negotiations, performance reviews, client calls, hard feedback, the conversations you care about.

See the research library behind every suggestion

Add your own documents to the assistant

See what Kennan does