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.

Using Agent Teams as a Product Backend: Bridging Swift Desktop Apps to Claude Agent SDK

Fazm Team·March 17, 2026·2 min read

swift claude-sdk architecture macos agent-teams

Using Agent Teams as a Product Backend: Bridging Swift Desktop Apps to Claude Agent SDK

Building a native macOS app that needs AI capabilities presents an architectural question - how do you connect a Swift frontend to an LLM agent backend? The answer we landed on is a local Node.js process running the Claude Agent SDK, bridged to our Swift app through a lightweight communication layer.

The Architecture

The Swift app handles everything visual - the menu bar interface, system permissions, screen capture, accessibility API access. It is a proper native macOS citizen. But when it needs to reason, plan, or make decisions, it delegates to a local Node.js process running the Claude Agent SDK.

Communication happens over local IPC. The Swift app sends context - screen state, user instructions, accessibility tree data - and the Node.js agent returns structured actions to execute. The Swift app then executes those actions through native macOS APIs.

Why Not Pure Swift?

Swift does not have native support for the Claude Agent SDK. You could make raw API calls, but you would lose the agent loop, tool use, and multi-turn conversation management that the SDK handles. Reimplementing all of that in Swift is months of work for no real benefit.

The Node.js bridge gives you the full agent SDK with all its capabilities while keeping the frontend native. Users get instant app launch, proper macOS integration, and low memory usage from Swift. The AI reasoning happens in a background process they never see.

Agent Teams as Backend

The interesting part is treating multiple agents as your product backend. One agent handles email triage. Another manages browser automation. A coordinator agent delegates between them. This is not a monolithic backend - it is a team of specialized agents, each with their own tools and context.

This pattern works well for desktop apps because each agent can be scoped to specific permissions and capabilities, matching the tiered trust model that desktop automation requires.

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

Using Agent Teams as a Product Backend: Bridging Swift Desktop Apps to Claude Agent SDK

Using Agent Teams as a Product Backend: Bridging Swift Desktop Apps to Claude Agent SDK

The Architecture

Why Not Pure Swift?

Agent Teams as Backend

More on This Topic

Related Posts

Structuring a macOS Agent App with Modular Swift Frameworks

Best Practices for Shipping iOS and macOS Apps with Claude Code

Claude Code for Swift/macOS Development - ScreenCaptureKit and Deprecated APIs