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.

Does Fazm work in languages other than English?

Yes. Fazm works in any language - English, Russian, Spanish, German, Japanese, and more. You can speak or type in your preferred language and Fazm will understand and act. Some of our most active users run their entire workday in Russian, issuing voice commands to manage Jira tickets, write Slack messages, and navigate internal tools. There is no language setting to configure - just speak or type naturally and Fazm handles it.

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.

Controlling AI Agent Swarms with tmux - the Scrappy Approach That Works

Fazm Team·March 18, 2026·2 min read

agent-swarm tmux terminal orchestration productivity devtools

Agent Swarms via tmux

While everyone debates the best orchestration framework for AI agent swarms, a surprisingly effective approach is already sitting in your terminal: tmux. No fancy infrastructure, no complex deployment pipelines - just terminal sessions running agents in parallel.

The Basic Setup

The pattern is dead simple. tmux new-session -d -s agent-name spins up a detached session. Run your agent command in it. Repeat for as many agents as you need. Each agent gets its own named session that you can attach to, inspect, and kill independently.

Want to check on agent-3? tmux attach -t agent-3. Want to see all running agents? tmux list-sessions. Want to kill one that's stuck? tmux kill-session -t agent-stuck. The primitives are already there.

Why This Beats Orchestration Frameworks

For teams running fewer than ten agents, tmux has zero overhead. No YAML configs, no container orchestration, no message queues. Your agents are just processes in terminal sessions. You can see their output in real time, pipe logs to files, and restart individual agents without affecting others.

The debugging experience is also superior. When an agent goes wrong, you attach to its session and see exactly what happened. No digging through distributed logs or tracing systems.

Adding Structure

As you scale, add lightweight conventions on top. Name sessions consistently - agent-social-poster, agent-code-reviewer, agent-data-monitor. Use a simple shell script to start your full swarm with one command. Pipe each agent's output to a log file for post-mortem analysis.

You can even add health checks - a cron job that runs tmux list-sessions and alerts you if an expected agent isn't running.

When to Graduate

tmux stops scaling around 15-20 agents, or when you need agents on multiple machines. At that point, look into proper orchestration. But for most teams experimenting with agent swarms, tmux is the right starting point - simple, debuggable, and immediately productive.

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

Controlling AI Agent Swarms with tmux - the Scrappy Approach That Works

Agent Swarms via tmux

The Basic Setup

Why This Beats Orchestration Frameworks

Adding Structure

When to Graduate

More on This Topic

Related Posts

tmux Beats Multiple IDE Windows for Managing AI Agents

Agent Teams vs Dedicated Concurrency - Orchestration or Tmux Sessions

Orchestrator Implementor Review Loop - Code Review with tmux Claude Code Sessions