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.

What v0.1.14 Taught Us About macOS Accessibility API Automation

Fazm Team·March 17, 2026·3 min read

mcp-server macos accessibility-api v014 iteration open-source

What v0.1.14 Taught Us About macOS Accessibility Automation

Fourteen releases into building an MCP server for macOS accessibility control, the lessons are clear. The hard parts aren't where you'd expect them.

The API Is Deceptively Simple

Apple's accessibility API surface is small. You can query elements, read attributes, perform actions. The basics work in an afternoon. But production reliability takes months. Every app implements accessibility differently. SwiftUI apps expose a clean tree. AppKit apps vary wildly. Electron apps are a grab bag.

What Broke Between Versions

v0.1.8 broke Finder navigation. Apple changed how Finder exposes sidebar items in a minor macOS update. No documentation. No changelog mention. We found out from user bug reports.

v0.1.11 introduced a memory leak. Retaining accessibility element references without releasing them. The server would grow to 2GB over a few hours of heavy use. Fixed by implementing proper reference counting in the element cache.

v0.1.13 fixed the menu bar race condition. Clicking a menu item sometimes failed because the menu would dismiss before the click registered. The fix was adding a small delay after menu expansion - ugly but necessary.

Lessons for MCP Server Builders

Test with real apps, not synthetic UIs. Your test harness might have perfect accessibility support. Safari, Slack, and VS Code each have their own quirks that only show up in production.

Cache aggressively, invalidate carefully. The accessibility tree changes constantly. Caching element references speeds up traversal but stale references cause crashes. We settled on a 500ms cache TTL as a reasonable default.

Error messages matter. When an element can't be found, tell the agent why. "Button not found" is useless. "Button 'Submit' not found in window 'Settings' - window contains: Cancel, Apply, Reset" gives the agent enough context to recover.

Ship often. Each release fixes edge cases you didn't know existed. Users are running your server against apps you've never tested. Frequent releases build trust and surface issues faster.

The State of Desktop Automation

We're still early. The accessibility API is powerful but undersupported by app developers. As more AI agents rely on it, there's pressure for apps to improve their accessibility support - which benefits everyone, not just AI tools.

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

What v0.1.14 Taught Us About macOS Accessibility API Automation

What v0.1.14 Taught Us About macOS Accessibility Automation

The API Is Deceptively Simple

What Broke Between Versions

Lessons for MCP Server Builders

The State of Desktop Automation

More on This Topic

Related Posts

How an MCP Server Lets Claude Control Any Mac App

Building an MCP Server for macOS Accessibility API Control - Release Notes and Lessons

Building an MCP Server for Native macOS App UI Control