Who it is forA developer who wants a visual workbench instead of a terminal for running the Grok Build agent on a local codebase.
The problemRunning the agent only in a terminal makes it hard to track several tasks, review edits, and keep project context organized.
The outcomeA trusted project open in the desktop app with an agent session running under Ask permission mode.
What you need first
- Grok Build CLI (grok) version 0.2.112 or newer, installed and signed in, or an API key or custom relay configured in the app
- A project folder you are willing to let the agent work in
- Git installed if you plan to use Git worktrees or Git diff review
Steps
- Download the installer for your platform from Grok App.com or the GitHub Releases page.
- Launch Grok App and let the setup wizard verify the Grok Build CLI, or run
grok updatein a terminal if the CLI is already installed. - On the account step, choose Use existing CLI sign-in if your local grok CLI is already authenticated.
- Add your project by selecting its working directory and trusting it.
- Choose Ask as the permission mode and start a session with a first prompt.
Prompt for your agent
Using the Grok App repo (https://github.com/RongleCat/grok-app), set up the desktop workbench and open the project at <project-path> as a trusted workspace in Ask permission mode. Expected output: a running agent session tied to that project. Verify that the grok CLI version is 0.2.112 or newer before starting.
Caveat. Grok App is not an official xAI product and needs a working local grok CLI for full agent capabilities.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page