How much time will I actually save with Fazm?

Most users report saving 45-90 minutes per day on repetitive tasks. The biggest time savings come from email management (drafting replies, sorting, archiving), form filling (expense reports, CRM updates, applications), research (comparing products, gathering data from multiple sites), and social media (cross-posting, scheduling, replying). For example, booking a flight that normally takes 10 minutes of clicking through airline sites takes a single voice command with Fazm. Filing an expense report that requires opening a PDF, extracting numbers, and entering them into a spreadsheet becomes one spoken sentence. The more repetitive and multi-step your daily work is, the more time you get back.

What exactly can Fazm control?

Fazm controls everything you can do manually on your Mac. That includes mouse movements and clicks, keyboard typing, browser navigation and form filling, app switching, file management in Finder, and system-level actions. It uses direct browser DOM control for web interactions - meaning it reads and manipulates the actual page structure rather than taking screenshots and guessing where to click. For native macOS apps, Fazm uses accessibility APIs to interact with buttons, menus, text fields, and other UI elements. This works across any application: Chrome, Safari, VS Code, Slack, Figma, Terminal, Mail, Calendar, and more.

How is Fazm different from ChatGPT or Claude?

Chatbots like ChatGPT and Claude give you answers in a conversation window. Fazm takes action directly on your computer. When you say 'reply to Sarah's email,' Fazm opens your email app, finds Sarah's message, writes a contextual reply, and sends it. A chatbot would tell you what to write, but you still have to do all the clicking and typing yourself. Fazm moves your mouse, types on your keyboard, clicks buttons, and navigates between apps. It is a computer agent, not a chat assistant.

How does the memory layer work?

Fazm builds a personal knowledge graph by extracting information from your files, browsing history, conversations, and daily activity. Over time, it learns your contacts (names, emails, relationships), accounts and credentials, preferences (formatting, tone, scheduling habits), and frequently used workflows. In your first week, you might say 'Reply to Sarah's email, she's my cofounder, her email is sarah@acme.com.' By week four, you just say 'Reply to Sarah' because Fazm already knows who she is. By week eight, Fazm can draft the reply before you even ask. All of this data stays locally on your Mac - your knowledge graph never leaves your machine or gets sent to any cloud service.

Is Fazm safe? Can it mess up my computer?

Safety is built into every layer of Fazm. You watch every action in real-time on your screen - Fazm moves your mouse and types visibly, so there is nothing hidden. You can stop any action at any point by pressing a keyboard shortcut. Fazm also shows you what it plans to do before executing destructive actions like deleting files or sending emails, giving you a chance to confirm or cancel. Because Fazm is open source, the code is fully auditable on GitHub. There is no hidden behavior, no background processes making changes you cannot see, and no actions that bypass your screen.

What platforms does Fazm support?

Fazm currently supports macOS, running natively on both Apple Silicon (M1, M2, M3, M4) and Intel Macs. It is built with Swift and uses macOS-specific frameworks like ScreenCaptureKit for screen analysis and Accessibility APIs for app control, which is why macOS is the primary platform. Windows and Linux support are on the roadmap but do not have release dates yet. You can also control your Mac remotely from your phone using Fazm Remote, which gives you voice access to your desktop while you are away from your computer.

How does Fazm voice input work?

One keyboard shortcut activates push-to-talk. Hold the key, speak naturally about what you need done, and release. Fazm transcribes your speech locally using on-device models, so there is no network latency for the voice recognition step. You do not need wake words like 'Hey Siri' or 'OK Google' - just press and talk. You can also type commands into the floating toolbar if you prefer text input. Fazm understands natural language, so you do not need to memorize specific commands. Say 'book me a flight to Tokyo next Thursday' or 'find the cheapest AirPods on Amazon' and Fazm figures out the steps.

Is my data sent to the cloud?

Fazm processes screen analysis and memory entirely on your machine. The personal knowledge graph, file indexing, and screen capture all run locally. The only data that leaves your Mac is the intent - a text description of what you want to accomplish, which is sent to the AI model (Claude or GPT) for action planning. Your actual screen content, file contents, browsing history, and personal knowledge graph never leave your computer. Fazm is also open source, so you can verify exactly what data is transmitted by reading the code on GitHub. For users who need complete air-gapped operation, local model support is planned.

Back to Blog

Building a Floating Toolbar in SwiftUI for macOS - Lessons from a Desktop Agent

Fazm Team·March 17, 2026·3 min read

swiftuimacostoolbarui-designmenu-bar

Building a Floating Toolbar in SwiftUI for macOS

Building a floating toolbar that feels native on macOS is harder than it looks. Apple Notes, Xcode, and Spotlight all have floating panels with smooth animations and correct behavior around fullscreen apps, multiple displays, and keyboard shortcuts. Getting there with SwiftUI requires solving a few specific problems.

Window Configuration

The foundation is an NSPanel subclass rather than a regular NSWindow. Panels have the right default behavior for floating UI - they do not appear in the window switcher, they can float above other windows, and they handle focus correctly.

Key settings:

styleMask includes .nonactivatingPanel so clicking the toolbar does not steal focus from the active app
level set to .floating keeps it above regular windows
collectionBehavior includes .canJoinAllSpaces and .fullScreenAuxiliary for proper multi-desktop and fullscreen behavior

Layout With @State

The toolbar needs to track its own size because SwiftUI does not give you a reliable way to measure content after layout. Use a GeometryReader inside the toolbar content to report the size back to an @State property, then apply that size as the frame of the hosting window.

This creates a feedback loop - content determines window size, which determines available space. Break the loop by using .fixedSize() on the toolbar content so it always reports its intrinsic size rather than expanding to fill available space.

Smooth Expand and Collapse

When the toolbar expands (showing additional controls) or collapses, animate both the SwiftUI content and the window frame together. Use withAnimation for the content and NSAnimationContext for the window frame, matching the duration and timing curve.

The trick is animating the window frame from the correct anchor point. If your toolbar is pinned to the top of the screen, the frame should grow downward. Calculate the new origin as currentOrigin.y - heightDelta and set the frame in the same animation block.

Keyboard Height Tracking

If the toolbar includes a text field, the macOS virtual keyboard (on iPads connected to a Mac or accessibility keyboards) can overlap it. Listen for NSApplication.didChangeScreenParametersNotification and adjust the toolbar position when the available screen area changes.

These patterns combine into a floating toolbar that feels like a native macOS component rather than a web-style overlay.

Fazm is an open source macOS AI agent. Open source on GitHub.

Building a Floating Toolbar in SwiftUI for macOS - Lessons from a Desktop Agent

Building a Floating Toolbar in SwiftUI for macOS

Window Configuration

Layout With @State

Smooth Expand and Collapse

Keyboard Height Tracking

Related

Related Posts

Why Native Swift Menu Bar Apps Are the Right UI for AI Agents

Building an Intelligent macOS Sidebar That Actually Blends Into Your Desktop

Why We Build AI Tools with SwiftUI Instead of Electron