Grok Build was still working.
Your Mac didn't care.

If macOS went to sleep mid-task, Grok Build — xAI's terminal coding agent — froze right where it was. It didn't fail; it got paused along with your Mac. Here's why that happens, and how to stop it.

To keep your Mac awake while Grok Build runs: the free way is macOS's built-in caffeinate — start your session as caffeinate -i grok and the Mac can't idle-sleep until the agent exits. The automatic way is AgentBarista (14-day free trial, then $19 one-time), which watches for real agent activity and lets your Mac sleep once the work is done.

The direct answer

Why your Mac sleeps while Grok Build is still going

Grok Build spends most of a task waiting on a model response — which barely uses any CPU. macOS only looks at CPU and user input to decide whether to sleep, so an agent that's "thinking" hard but computing little looks idle to the OS. After your screen-sleep or system-sleep timer runs out, macOS suspends the Mac, and the Grok Build process is frozen along with everything else until you wake it back up.

This bites hardest exactly where Grok Build is meant to shine: Plan Mode approvals, parallel subagents chewing through a long task, or a headless run left going overnight. The fix is to stop macOS from sleeping for as long as the agent is actually running — then let it sleep normally again once the run is done. You can do that for free in two minutes, or with a tool that watches for real agent activity so you don't have to babysit it.

The free option

Free tools can keep your Mac awake too

If you only run Grok Build occasionally, you don't need to buy anything. Because Grok Build is a terminal agent, the cleanest free fix is one command:

  • The built-in caffeinate command. Launch your session as caffeinate -i grok instead of grok. The Mac can't idle-sleep while the agent runs, and the moment Grok Build exits, normal sleep is allowed again — nothing to remember to undo. Already on your Mac, free. For a headless / CI run, wrap the whole command the same way: caffeinate -i <your command>.
  • Amphetamine (free, Mac App Store). A menu-bar toggle to keep the Mac awake on a timer or while your terminal app is open — handy if you'd rather flip a switch than type a command.

Both are a fine choice if Grok Build runs for a few minutes here and there. The catch: neither one knows when the agent actually finished a task versus when it's just sitting at an idle prompt. You either stop it yourself, or it keeps your Mac awake — and your battery draining — long after the work is done.

The purpose-built option — honest status

What AgentBarista does today for Grok Build

Straight answer: Grok Build is new enough (xAI shipped it in 2026) that it isn't in AgentBarista's calibrated agent list yet — we verify each tool's process name and activity signals on a real Mac before we call it "supported," and we haven't finished that for Grok Build. Add it to your custom target-app list and AgentBarista's general CPU-activity detection will watch it today — and for a terminal agent like this, CPU detection is exactly the signal that works best. The tuned detection that also catches long silent "thinking" turns at 0% CPU is calibration-in-progress.

Works today via CPU detection

Add Grok Build to your target-app list and AgentBarista keeps the Mac awake whenever it's burning real CPU — the same fallback every agent gets before it's individually tuned, and a strong signal for a terminal agent.

Calibrated support: in progress

We're verifying Grok Build's process name and activity so the silent, model-waiting turns get caught too, not just active CPU. We ship new-agent support fast — check the changelog for when this lands.

Has a safety net regardless

A battery cutoff and an emergency restore mean it never gets permanently stuck keeping your Mac awake — true for every app AgentBarista watches, calibrated or not.

Grok Build (CPU fallback, tuning in progress) Claude Code Cursor Codex Gemini CLI Copilot CLI OpenCode Zed Antigravity Claude ChatGPT + more

It runs on your Mac. AgentBarista never opens your files. To tell a working agent from a finished one it looks at process command lines and CPU, at the names and modification times of your agents' session files, and — only if you grant macOS Accessibility permission — at the on-screen text of the agent apps you enable and of the terminals we support. Two of those can contain your own words: a command line includes any prompt you pass on it, and on-screen text includes whatever is visible in that window, your code included. Both are matched against status phrases on your Mac and discarded on the spot: never stored, never sent. Nothing about your work leaves your Mac — no file contents, no code, no prompts, no file names, no activity data. Your stats and settings stay on this Mac. The app contains no analytics or telemetry of any kind. Its one network call is license validation, sent to our payment provider, Lemon Squeezy: activating a license sends your license key and your Mac's name, and the routine check after that sends your license key and an anonymous instance id — nothing else.

Pricing

Try it free, then keep it. No subscription.

Pro, one-time
$19 once
  • 14-day free trial, no card needed
  • $15 founding price for the first 200 customers
  • Includes 1 year of updates
  • Lifetime option: $39 once, updates forever
Get notified at launch

Not live yet — leave your email and we'll ping you the moment it is.

Running agents across a team instead? See team pricing.

More agents

Also running Claude Code, Codex CLI, or another agent?

Same Mac-goes-to-sleep problem, different tool. Each of these guides covers the fix for that agent specifically: