Stop clicking. Start asking.

Hey Happy,

Say what you want out loud. Happy does it on your computer, tells you how it went, and shows every step. Free and open source, for Mac and Windows.

Setup is one window: it finds your model, gets the speech models ready, and you press Start. For macOS 13 or later and Windows 10 or 11. It isn't signed yet, so the first time choose Open Anyway on a Mac, or More info › Run anyway on Windows.

Ready when you are

Six steps, or one sentence.

Pick something you do every day. Happy finishes while the old way is still going.

The old way0 of 6 done

    Six steps you get to skip.

    HappyReady when you are

      1. Ask

        Say “Hey Happy” and keep talking, or hold the right Option key (right Ctrl on Windows). Typing works too.

      2. Watch

        Happy picks the tools for the job. Click its smile and every step is there, with what went in and what came back.

      3. Hear

        It answers out loud, and says what it's doing on longer jobs. Say “wait” and it holds; ask something new and it listens.

      Ask it for anything you'd do yourself

      Brightness, volume and play/pause don't even wait for a model, so they happen the moment you finish speaking.

      It works with what you already use

      Happy finds what's set up on your computer, and you can add more in a minute.

      WhatsApp, built in

      Link it once with a QR code, then read, search and send messages and files by voice. Away from your desk? Text Happy's own chat from your phone and it does the job on your computer.

      Gmail, Notion and more

      Happy speaks MCP, the standard most AI tools use to reach services. Paste the install line a service gives you, and it's ready. Already use Claude Desktop or Cursor? Your services come with you.

      Your browser and apps

      It works pages in your own Chrome, signed in as you, and clicks, types and picks menus in your apps by the words on their buttons.

      Your coding agent

      Ask for something to be built and Happy hands it to Claude Code, Codex or another agent you have, in a Terminal window you can watch.

      Your model. Your privacy.

      Choose what Happy thinks with. Each choice shows what it needs and where your requests go.

      What you need
      Claude Code, signed in with a Pro or Max plan.
      What it costs
      Nothing extra. It uses the plan you already have.
      Where your requests go
      To Anthropic, through your own Claude Code.
      Good to know
      Your claude.ai connectors, like Gmail and Drive, come along.

      Whichever you choose, these stay on your computer

      • Your voice. Speech becomes text on your computer, and it's only acted on when you talk to Happy.
      • Happy's voice. The voice you hear is made on your computer.
      • Your history. Every request, step and answer is saved in a file here, not in an account.
      • Your keys. API keys and sign-ins are stored here and never shown again in full.

      Yours to shape

      Tell Happy something once and it keeps it. Give it a name and a voice, and it's yours.

      • “My brother is John in my contacts.”Tomorrow, “text my brother” just works.
      • “Remind me to call the dentist at four.”Said back in full, so a wrong guess is heard. Daily, hourly or on weekdays.
      • “Save that as a routine called morning brief.”Then “morning brief”, or “run it every weekday at 7”.
      • “From now on, talk like a knight.”Or paste a whole script, and it learns the way people talk in it.

      “Hey Happy, what's the weather?”

      The name is the wake word, so “Happy” in the middle of a sentence to someone else does nothing. Then pick one of 14 voices and how fast it talks.

      Open source, every line

      Happy is free under the MIT license: the app, its prompts and its setup. Read it, change it, and send improvements back.

      Install from source

      git clone https://github.com/thepropotato/happy.git
      cd happy
      ./setup.sh

      On Windows, run .\setup.ps1 instead of ./setup.sh.

      Questions

      Is it really free?

      Yes. Happy costs nothing. If you use Claude or an API key, you pay that provider as usual; a model on your own machine is free.

      Is it always listening?

      It listens for its name and turns speech into text on your computer, acting only when you address it. Turn the wake word off and it listens only while you hold the key.

      Will it do things without asking?

      It does what you asked, and every step is on screen. When a message could reach the wrong person, like a name that fits two contacts or someone you've never messaged, it checks first.

      Does it work offline?

      With a model on your own machine, everything on your computer works offline: apps, files, settings and reminders. Web searches, WhatsApp and email need the internet.

      Does Happy collect anything?

      Not unless you turn on “Help make Happy better” under Privacy in the settings. Then each turn sends anonymous counts: which tools ran, how long it took, and whether it worked. Never your words, Happy's replies, files or contacts, and the settings show exactly what was last sent.

      Can I use it without speaking?

      Yes. Type in the panel, or write to Happy's own WhatsApp chat from your phone. It answers there, quietly.