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

Managing Multiple Codebases with Claude Code - Swift, Python, TypeScript in One Project

Fazm Team·March 17, 2026·2 min read

multi-codebaseclaude-codeswiftpythontypescript

Managing Multiple Codebases with Claude Code

Building Fazm means working across three languages simultaneously. The macOS app is Swift. The AI backend is Python. The website and dashboard are TypeScript. They all talk to each other through APIs and shared data formats.

The hardest part is not writing code in three languages. It is keeping the AI assistant aware of how changes in one codebase affect the others.

The Cross-Codebase Problem

You change a Python API endpoint's response format. Now the Swift app's decoder breaks. Claude Code does not automatically know about this because it is working in the Python project. By the time you switch to the Swift project and ask it to fix the build error, it has no context about what changed on the backend.

The fix is documentation. A shared CLAUDE.md file that describes the API contract between components. When the Python endpoint changes, you update the spec, and the Swift-side Claude session reads the updated contract.

Practical Workflow

Run separate Claude Code sessions for each codebase. Do not try to cram everything into one massive context window. Each session gets its own CLAUDE.md with language-specific conventions and cross-references to shared contracts.

For shared types, maintain a single source of truth. We use JSON Schema files that both the Python and Swift codebases reference. When the schema changes, both sides know about it.

What Works

Dedicated CLAUDE.md per codebase with clear API contracts
JSON Schema as the shared type system
Running parallel Claude Code sessions in separate tmux panes
Committing API changes with clear descriptions that the other session can reference

What Does Not Work

Asking one session to "also fix the Swift side" when it is in the Python project
Relying on the model to remember cross-project details between sessions
Skipping the documentation step because "it is just a small change"

Every small undocumented change becomes a debugging session later.

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

Managing Multiple Codebases with Claude Code - Swift, Python, TypeScript in One Project

Managing Multiple Codebases with Claude Code

The Cross-Codebase Problem

Practical Workflow

What Works

What Does Not Work

Related Posts

Running 5 Parallel AI Agents Is Making My API Bill a Second Rent Payment

How to Design App Icons with Claude Code - No Figma Required

Parsing Claude Code's JSONL Format for macOS Dev Tools