Use the Claude Code Desktop App for a Persistent Window Outside Your Terminal
Running Claude Code in a terminal tab works, but it's easy to lose it in a stack of other tabs — or accidentally close it mid-session. The desktop app gives Claude Code its own window that lives outside your terminal entirely.
Download it from the official site for Mac or Windows. Once installed, it launches like any other app — Spotlight, dock, taskbar, whatever you prefer.
The desktop app runs the exact same Claude Code underneath. Your CLAUDE.md, hooks, MCP servers, custom commands, and settings all work identically. The only difference is where the window lives.
A few reasons the desktop app works better for some workflows:
- Persistence — the window survives terminal restarts, shell crashes, and accidental
Cmd+Won the wrong tab. Your session just keeps running. - Dedicated space — Claude gets its own window in your window manager, separate from your terminal multiplexer or tab setup. Alt-Tab or Cmd-Tab straight to it.
- Multiple instances — open several desktop windows for different projects, each pointing at a different directory. Cleaner than juggling terminal tabs.
- Keyboard shortcut — assign a global hotkey to toggle the Claude Code window so you can summon it from any app instantly.
You can also access Claude Code through the web app at claude.ai/code if you want to work from a browser without installing anything. Same capabilities, accessible from any machine with a browser.
All three — CLI, desktop app, web app — share the same session system. Start a conversation in the desktop app, continue it later from the CLI with --continue, or pick it up on another machine through the web.
Pick the surface that fits your workflow — terminal, desktop, web, or IDE — Claude Code works the same everywhere.
via Claude Code
Log in to leave a comment.
Set up Claude Code as an automated reviewer in your CI pipeline — on every pull request, it reads the diff, checks for bugs, security issues, missing tests, and convention violations, then posts its findings as a PR comment. Your human reviewers get a head start because the obvious issues are already flagged before they look.
Before deploying, tell Claude to read your project — migrations, environment variables, queue workers, scheduled tasks, caching, third-party integrations — and generate a deployment checklist that's specific to your app. Not a generic "did you run migrations?" list, but one that knows YOUR infrastructure and catches the things YOUR deploy can break.
Instead of writing a README from memory or copying a template, tell Claude to read your project and generate one that's actually accurate — real setup instructions from your config, real architecture from your directory structure, real API examples from your routes, and real prerequisites from your dependency files.