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

The Gap Between Agent Memory and Agent Execution - You Need Both

Fazm Team·March 17, 2026·2 min read

agent-architecturememoryexecutionmcpdesktop-agent

The Gap Between Agent Memory and Agent Execution

Building Fazm taught us that an AI agent has two halves that are equally important and usually developed unevenly: memory (what the agent knows and remembers) and arms (what the agent can actually do).

Most projects start with one and neglect the other.

The Arms Problem

The first version of Fazm was essentially Claude with access to the macOS accessibility API through an MCP server built in Swift. We called it "building the arms" - giving the AI the ability to physically interact with the desktop.

This MCP server wraps macOS accessibility APIs so the agent can:

Enumerate every UI element in any running application
Click buttons, fill text fields, select menu items
Read the current state of any window or dialog
Capture screenshots for visual verification

Without these arms, the agent is just a chatbot. It can talk about opening Slack and sending a message, but it cannot actually do it.

The Memory Problem

Arms without memory create a different problem: the agent that forgets everything. Every session starts from zero. It does not remember your preferences, your workflow patterns, which apps you use for what, or what it tried last time that did not work.

This is the gap most desktop agents fall into. They can execute actions but have no persistent understanding of the user's environment.

Bridging the Gap

The solution is building both systems and connecting them:

Execution layer. MCP servers that wrap OS-level APIs for actual desktop control.
Memory layer. Persistent storage of user preferences, workflow patterns, and action history that carries across sessions.
Planning layer. The LLM that sits between memory and execution, using what it knows about you to decide what to do and how to do it.

An agent with great memory and no arms is a note-taking app. An agent with great arms and no memory is a macro recorder. You need both to build something that actually feels like an assistant.

The Gap Between Agent Memory and Agent Execution - You Need Both

The Gap Between Agent Memory and Agent Execution

The Arms Problem

The Memory Problem

Bridging the Gap

More on This Topic

Related Posts

Desktop Agents Can Control Apps but Lack the WHY - Cross-Channel Context Matters

Giving Claude Code Eyes and Hands with macOS Accessibility APIs

What's Missing from Manus and Every Other Desktop Agent - Persistent Memory