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.

MCP Tool Responses Are the Biggest Context Hog - How to Compress Them

Fazm Team·March 17, 2026·3 min read

mcp context-window accessibility-api optimization token-management

MCP Tool Responses Are the Biggest Context Hog - How to Compress Them

You are halfway through a complex task with your AI agent and suddenly hit the context limit. You check the token usage and discover that 80% of your context window is filled with MCP tool responses you never even read.

This is the dirty secret of MCP-based workflows. Every tool call returns a full response that stays in the conversation context. A single accessibility tree traversal can return 50,000+ tokens of nested UI element descriptions. Three traversals and you have burned through most of a 200k context window on raw data.

Where the Tokens Go

The biggest offenders are tools that return structured data about the current state of something - accessibility trees, DOM snapshots, file listings, API responses with nested objects. Each one is useful for the agent to process, but the raw data does not need to persist in context after the agent has extracted what it needs.

A macOS accessibility tree for a moderately complex app window can easily be 20,000-50,000 tokens. Browser DOM snapshots are even worse. And these grow linearly with each interaction - every click triggers a new snapshot.

Compression Strategies

The most effective approach is filtering at the source. Instead of returning the entire accessibility tree, return only the elements that match a relevance filter. If the agent is looking for a button to click, it does not need every static text label on the screen.

Another approach is response compaction - summarizing MCP responses into structured data before they enter the conversation context. Instead of the full tree, store a list of actionable elements with their references.

You can also use output modes that skip embedding images and large binary data directly in the response. Saving screenshots to files instead of base64-encoding them into the conversation saves hundreds of thousands of tokens per session.

The Real Fix

The underlying problem is that MCP was designed for single-turn interactions, not long multi-step workflows. A proper solution would let the agent query past tool results without keeping them in the active context window. Until then, aggressive compression is the best defense.

MCP Tool Responses Are the Biggest Context Hog - How to Compress Them

MCP Tool Responses Are the Biggest Context Hog - How to Compress Them

Where the Tokens Go

Compression Strategies

The Real Fix

More on This Topic

Related Posts

Accessibility Tree Dumps Overflow LLM Context Windows - How to Fix It

Why Backend Tasks Still Break AI Agents - Tool Response Design Matters

Giving Claude Code Eyes and Hands with macOS Accessibility APIs