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.

Back to Blog

Building Autonomous Agent Loops That Run Overnight on macOS

Fazm Team·March 17, 2026·3 min read

autonomous-agentscronlaunchdmacosplaywrightnightly-buildsautomation

Building Autonomous Agent Loops That Run Overnight

The most productive hours for an AI desktop agent are the ones when you are asleep. Set up a cron loop, point it at your task queue, and wake up to completed work.

Here is how to build reliable overnight agent loops on macOS.

The Architecture

A typical autonomous loop has three components:

Scheduler - a launchd plist or cron job that fires at regular intervals
Task source - a queue of work items the agent pulls from (could be a file, a database, or an API)
Execution layer - the agent runtime with access to both native macOS apps (via MCP servers) and web browsers (via Playwright)

The scheduler fires hourly or at whatever cadence makes sense. The agent picks up the next task, executes it, logs the result, and exits cleanly.

Native Apps vs Web

Overnight agents typically need two different interaction modes:

macOS MCP server for native applications - controlling Finder, Mail, Calendar, or any app that exposes Accessibility API elements
Playwright for web automation - logging into dashboards, scraping data, posting content, filling forms

The key is that both modes work without a visible display. Native macOS apps can be controlled through Accessibility APIs even when the screen is locked. Playwright runs a headless browser by default.

Practical Considerations

Running agents overnight introduces challenges you do not face during interactive use:

Error recovery - the agent must handle failures gracefully since no human is available to intervene
Timeout management - set hard time limits per task to prevent a single failure from blocking the entire queue
Resource cleanup - close browser instances and release memory between tasks
Idempotency - tasks should be safe to retry if the agent crashes mid-execution
Wake/sleep handling - configure macOS power settings to prevent the machine from sleeping during scheduled runs

A Minimal Setup

Create a launchd plist that runs your agent script every hour. The script should pull one task from the queue, execute it with a 10-minute timeout, log the result to a dated file in /tmp, and exit. Keep the first version simple - complexity should come from observed failures, not anticipated ones.

Start with low-stakes tasks like data collection and monitoring. Graduate to actions that modify state only after you trust the error handling.

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

Building Autonomous Agent Loops That Run Overnight on macOS

Building Autonomous Agent Loops That Run Overnight

The Architecture

Native Apps vs Web

Practical Considerations

A Minimal Setup

More on This Topic

Related Posts

Invisible Agents on Launchd Crons - No Chat Interface Needed

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

Building an AI Agent That Posts to Social Media on Your Behalf