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 Gateway Daemon for Claude Code Multi-Agent Scheduling

Fazm Team·March 17, 2026·2 min read

claude-code multi-agent daemon tmux launchd scheduling

Building a Gateway Daemon for Claude Code Multi-Agent Scheduling

Running multiple Claude Code agents manually works for a few hours. But when you want agents running overnight, on a schedule, or kicking off in response to events, you need a gateway daemon. The architecture is simpler than it sounds: tmux sessions with individual agents, launchd for scheduling, and a thin coordination layer.

The Architecture

Each agent runs in its own tmux session. This gives you isolation - one agent crashing does not take down the others - and visibility, since you can attach to any session to see what an agent is doing.

Launchd handles scheduling. A plist file tells macOS when to spin up agent sessions: nightly builds at 2 AM, test suite runs after each commit, documentation updates every Monday. Launchd is more reliable than cron on macOS because it handles missed executions when the machine was asleep.

The Coordination Layer

The gateway daemon is a lightweight script that sits between launchd triggers and agent sessions. It checks if an agent slot is available, reads the task queue, assigns work, and monitors output for completion signals.

The task queue is a simple directory of markdown files. Each file describes a task with acceptance criteria. The daemon picks the next file, creates a tmux session, starts Claude Code with the task as a prompt, and watches the session for the completion marker.

Knowing When to Intervene

This is the hardest part. An agent might be stuck in a loop, making the wrong architectural decision, or successfully completing something you did not actually want. The daemon needs heuristics for flagging sessions that need human attention.

Simple signals work well: no git commits in 15 minutes, repeated error messages, or the agent asking questions to stdin. The daemon can send you a notification when these thresholds are hit, and you attach to the tmux session to course-correct.

Start Simple

Do not over-engineer the daemon. Start with a bash script that manages two tmux sessions and a launchd plist for one scheduled task. Add complexity only when you hit a real limitation.

Building a Gateway Daemon for Claude Code Multi-Agent Scheduling

Building a Gateway Daemon for Claude Code Multi-Agent Scheduling

The Architecture

The Coordination Layer

Knowing When to Intervene

Start Simple

More on This Topic

Related Posts

Running 10+ Claude Code Agents Without Chaos - Tmux Orchestration

Schedule Claude Code Sessions With launchd to Use Your Token Quota Automatically

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