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.

What to Do with Your Idle Custom PC - Convert It to an AI Agent Server

Fazm Team·March 18, 2026·2 min read

homelab proxmox gaming-pc self-hosted local-ai

What to Do with Your Idle Custom PC - Convert It to an AI Agent Server

That gaming PC sitting under your desk collecting dust between sessions has serious compute potential. A mid-range gaming rig from the last few years - RTX 3080, 32GB RAM, fast NVMe - is more than enough to run local AI models and host always-on agent workflows.

Here is how to turn it into a productive AI agent server.

Why Proxmox

Proxmox gives you a hypervisor that runs VMs and containers from a web UI. You can allocate your GPU to a VM running Ollama for local inference while keeping separate containers for different agent workloads. If one agent crashes, it does not take down everything else.

Install Proxmox directly on the bare metal. It takes about 20 minutes. Your gaming setup becomes a proper server without buying any new hardware.

The Setup

A practical configuration looks like this:

VM 1: Ollama + local models - Pass through the GPU. Run Llama 3, Mistral, or whatever fits your VRAM. This handles the cheap inference tasks your agents need.
Container 1: Agent runtime - Your AI agent processes, scheduled tasks, and automation scripts.
Container 2: Support services - Databases, log aggregation, monitoring dashboards.

With 32GB of system RAM, you can comfortably run all three with room to spare.

GPU Passthrough

This is the most valuable part. Your RTX card sitting idle is wasted compute. With GPU passthrough to an Ollama VM, you get local inference at speeds that rival cloud APIs - without the per-token cost.

A 3080 with 10GB VRAM runs quantized 7B-13B models comfortably. A 4090 with 24GB handles 70B quantized models. Either way, it is free inference after the electricity bill.

Power and Noise

Gaming PCs are loud under load. Set a fan curve that keeps things quiet for sustained inference workloads - you do not need the same cooling profile as a gaming session. A typical setup draws 150-250W under AI workloads, which is roughly $15-25/month in electricity. Still cheaper than cloud inference.

Your idle hardware is your cheapest server.

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

What to Do with Your Idle Custom PC - Convert It to an AI Agent Server

What to Do with Your Idle Custom PC - Convert It to an AI Agent Server

Why Proxmox

The Setup

GPU Passthrough

Power and Noise

More on This Topic

Related Posts

Self-Hosted Voice Typing with Whisper for AI Agent Input

GPU Selection for Local AI Agent Workloads

Running AI Agents 24/7 on a Home Server