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.

Running Claude Code Over SSH on a Mac Mini M4 with tmux

Fazm Team·March 17, 2026·3 min read

mac-mini tmux ssh claude-code remote-development

Running Claude Code Over SSH on a Mac Mini M4 with tmux

The setup is simple but powerful - a Mac Mini M4 sits in a closet running 24/7 with tmux sessions for different agent tasks. SSH in from any laptop, tablet, or even a phone to manage everything.

Why a Dedicated Mac Mini

Your daily laptop has limitations for running AI agents continuously. It sleeps, it travels, it runs out of battery, and it gets slow when five Claude Code instances are fighting for resources. A dedicated Mac Mini M4 solves all of this:

Always on - launchd keeps it awake, no lid to close
Unified memory - 24GB or 64GB shared between CPU and GPU for local model tasks
Low power - draws about 10 watts idle, cheaper than a light bulb
macOS native - full access to accessibility APIs, screencapture, and native app control

The tmux Setup

Each tmux session runs a dedicated agent task:

pr-review - watches for new PRs and runs automated code review
social - handles social media posting on a cron schedule
monitor - checks production logs and alerts on anomalies
dev-1 through dev-3 - available for on-demand development tasks

When you SSH in, tmux attach -t pr-review drops you right into that agent's session. You can check its work, adjust instructions, or kill and restart it.

The Thin Client Experience

From your laptop, the workflow is: open terminal, ssh mini, tmux ls to see what is running, attach to whichever session needs attention. Your laptop does zero compute. All the token processing, file I/O, and agent execution happens on the Mini.

This means you can use a cheap laptop, an iPad with a terminal app, or even SSH from your phone in a pinch. The Mini is the brain. Everything else is just a screen.

Practical Tips

Use tmux set-option -g history-limit 50000 to keep enough scrollback for agent output
Set up SSH keys so you never type a password
Use mosh instead of SSH for unreliable connections
Run caffeinate -s to prevent sleep even without a display connected

The Mac Mini M4 as an always-on agent server is one of the highest-leverage hardware investments you can make.

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

Running Claude Code Over SSH on a Mac Mini M4 with tmux

Running Claude Code Over SSH on a Mac Mini M4 with tmux

Why a Dedicated Mac Mini

The tmux Setup

The Thin Client Experience

Practical Tips

More on This Topic

Related Posts

Building a Gateway Daemon for Claude Code Multi-Agent Scheduling

The Ideal Hardware Setup for Running Parallel Claude Code Agents

Running 10+ Claude Code Agents Without Chaos - Tmux Orchestration