AI assistants and search decision
Butler
A single competent developer can build and maintain a menu-bar ChatGPT client; the product has no evident durable moats and the core features are straightforward to reimplement.
Visit website↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off36 h to build
$20/mo3 h/mo upkeep
No published price to break even against.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Butler alternatives, with the arithmetic →
What a replacement has to do
- Open menu-bar app, press hotkey or click icon, send prompt to LLM via user-provided API key, receive and display response in compact UI.
What it still won’t have
- Packaged commercial desktop polish and installer/notarization handled for you
- Vendor-provided personal email support
- Paid one-time distribution (convenience of a released app and updates)
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Butler does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a macOS menu-bar ChatGPT client using Electron + React (or native SwiftUI if preferred) with a small Node backend process. Core features in scope: 1) menu-bar icon and compact chat window, 2) global hotkey to open the window, 3) send prompts to OpenAI-compatible LLMs using a user-entered API key, 4) secure local storage of the API key (OS keychain), 5) basic settings (model, max tokens), 6) error handling for API failures and rate limits, 7) packaging, code signing/notarization, and auto-update configuration. Out of scope: hosted API proxy, multi-user sync, server-side RAG, analytics dashboard. Require tests for API integration, hotkey behavior, and settings persistence, plus graceful error-handling and user-facing error messages.
How we checked
How the score was reached
- Build verdict base78
- An open-source build was found+5
- 3 cited sources+3
- 3/3 assessment runs agreed+4
- Evidence score90
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productButler — Home
- open sourceChatGPTNextWeb/NextChat
- open sourceSylinko/Everywhere
Integrity checks
What held up, and what did not.
