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.

Building a Desktop App to Orchestrate 5 Claude Agents in Parallel

Fazm Team·March 17, 2026·3 min read

swift desktop-app claude-code parallel-agents orchestration macos

Building a Desktop App to Orchestrate 5 Claude Agents in Parallel

Running multiple Claude Code agents from the terminal works, but a native desktop app takes the experience to another level. A Swift app that manages five agents in parallel gives you visual progress tracking, one-click task assignment, and automatic conflict detection - all in a native macOS interface.

Why a Desktop App

Terminal-based orchestration with tmux is functional but hard to monitor at a glance. A desktop app shows you:

Live status of each agent - working, waiting, completed, or stuck
Token usage per agent and total spend
File conflicts when two agents touch the same files
Output previews so you can review changes without switching contexts

The native SwiftUI interface updates in real time as agents report progress. You can see all five agents at once instead of cycling through tmux panes.

Architecture

The app spawns Claude Code processes through the command line, each in its own git worktree. A coordination layer tracks which files each agent is modifying and flags potential conflicts before they become merge problems.

Each agent gets:

A dedicated worktree cloned from the same base branch
A scoped task defined in natural language
A CLAUDE.md context file with project-specific instructions
An output channel that the app monitors for progress and completion

The Coordination Problem

The hardest part is not running five agents - it is making sure they do not step on each other. The app maintains a file-level lock map. When Agent 1 starts modifying auth.ts, Agent 3 gets a constraint added to its context: "Do not modify auth.ts - another agent is working on it."

This is not perfect. Semantic conflicts - where two agents make changes that individually work but break together - still require human review at merge time. But file-level coordination catches the obvious problems.

Results in Practice

Five agents working in parallel on genuinely independent tasks can compress a full day of work into about an hour. The key constraint is finding five tasks that are truly independent. Forced parallelism on coupled tasks creates more merge pain than it saves in time.

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

Building a Desktop App to Orchestrate 5 Claude Agents in Parallel

Building a Desktop App to Orchestrate 5 Claude Agents in Parallel

Why a Desktop App

Architecture

The Coordination Problem

Results in Practice

More on This Topic

Related Posts

Best Practices for Shipping iOS and macOS Apps with Claude Code

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

Claude Code vs Copilot: The Parallel Agents Advantage for Multi-Language Codebases