mo-browser-apps/icons

Generate macOS app icons using AI.

What it solves

It simplifies the creation of macOS app icons by automating the generation of the .icns format and the associated .iconset folder. It removes the need for manual design work or complex image processing to ensure icons meet macOS brand guidelines (such as squircle-friendly compositions).

How it works

The app uses the OpenAI API to generate images based on text prompts. It wraps user prompts in system constraints to ensure the output looks like a macOS icon. Users can provide an optional reference image to guide the layout or style. The workflow allows users to generate three variants, pick one, and then enter a "refine" mode where the chosen icon serves as a reference for further iterations.

Who it’s for

Developers and designers creating applications for macOS who need professional-looking icons in the correct technical format without manual design effort.

Highlights

  • AI-powered generation: Uses text prompts and reference images to steer image generation.
  • macOS-specific formatting: Automatically exports to .icns and .iconset formats.
  • Iterative refinement: Allows users to pick a variant and refine it further using the chosen image as a reference.
  • Realistic previews: Provides a squircle mask in the UI for a realistic preview of how the icon will look on macOS.

Related

  • Project
    apple/coreai-models

    A toolkit for exporting, authoring, and running open-source AI models on Apple silicon using the Core AI framework for macOS and iOS.

  • Project
    zhu-guli326/image2_UI_skill

    Image2 UI is an OpenAI‑Codex‑powered tool that converts screenshots, sketches, or text prompts into real, editable front‑end code with interactive logic and separate image assets. It supports recreate, redesign, and create workflows, runs on Node 20+ and Python 3.10+, and is MIT‑licensed.

  • Project
    openclaw/Peekaboo

    Peekaboo is a macOS‑only CLI and menu‑bar app that captures the screen, reads the accessibility tree, and performs native UI actions (click, type, press, etc.). It includes an LLM‑driven “agent” that can translate natural‑language instructions into sequences of these commands, and it can be exposed to external AI clients via a Model‑Control‑Protocol (MCP). Install via Homebrew, npm, or a signed DMG; configure model providers in `~/.peekaboo`. Ideal for GUI automation, testing, and building AI agents that control the desktop.

  • Project
    Code-with-Beto/snapai

    A CLI tool for mobile developers to generate app icons and Google Play feature graphics using OpenAI and Google Gemini image models.