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.

AI Agents That Learn Their Own Knowledge Graphs

Fazm Team·March 17, 2026·2 min read

knowledge-graphs ai-agents auto-learning memory agent-architecture

AI Agents That Learn Their Own Knowledge Graphs

The cold start problem kills most AI agent memory systems. A new agent knows nothing about your workflow, your tools, your preferences. You spend the first hour re-explaining everything you already told the last session. Auto-learning fixes this by letting agents build knowledge graphs from their own interactions.

The Cold Start Problem

Every time you start a fresh AI agent session, you lose accumulated context. The agent that perfectly understood your codebase yesterday is a blank slate today. Static config files like CLAUDE.md help, but they only capture what you thought to write down.

Auto-learning takes a different approach. The agent observes its own actions, the tools it uses, the patterns in your requests, and builds a knowledge graph over time. Each session adds nodes and edges to a persistent structure.

How ReachabilityGap Works

The most interesting concept in this space is ReachabilityGap - a framework where humans gate edge creation in the agent's knowledge graph. Think of it as a permission system for what the agent is allowed to learn and connect.

Without gating, an agent might create connections between sensitive data and external tools. It might link your private API keys to a deployment workflow and decide to use them autonomously. ReachabilityGap ensures that new edges in the knowledge graph require human approval before they become active paths the agent can traverse.

Why Human Gating Matters

Unrestricted auto-learning creates a security problem. An agent that freely builds its own knowledge graph will eventually create paths between things you do not want connected. The human gating step is not just about safety - it is about ensuring the knowledge graph reflects your actual workflow, not the agent's interpretation of it.

Practical Implementation

Start with a simple adjacency list stored in a JSON file. Each node is a concept, tool, or workflow step. Edges represent relationships the agent has observed. New edges go into a pending state until you approve them.

Over time, the approved graph becomes a rich model of how you actually work. The agent stops asking questions it has already learned the answers to.

AI Agents That Learn Their Own Knowledge Graphs

AI Agents That Learn Their Own Knowledge Graphs

The Cold Start Problem

How ReachabilityGap Works

Why Human Gating Matters

Practical Implementation

More on This Topic

Related Posts

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

AI Agent Capabilities Are Overhyped - Memory Is the Real Bottleneck

Fixing AI Goldfish Memory with CLAUDE.md Constraints