Overview
While cmd’s agent mode can autonomously take on complex tasks, you might prefer to bring in an external agent.Setting up Gemini CLI gives you access to powerful agentic capabilities through cmd’s native interface in Xcode.
Prerequisites
Before configuring Gemini CLI in cmd, you need to have Gemini CLI installed and set up on your system.1
Install Gemini CLI
Follow the official setup guide to install Gemini CLI.
2
Verify Installation
Ensure Gemini CLI is working properly and that your version is higher or equal to
0.20.0:3
Login in Gemini CLI
Launch Gemini CLI in your terminal to authenticate with your Google account or API key
Configuring Gemini CLI in cmd
Once Gemini CLI is installed and configured, you can enable it in cmd:1
Open AI Provider Settings
Go to Settings > AI Providers in cmd
2
Configuration
cmd should automatically detect where Gemini CLI is installed on your system.Otherwise, or if you need specific launch arguments, you can manually specify how to launch Gemini CLI
- Click “Add Provider” or “Configure” for Gemini CLI
- Provide the path to the Gemini CLI binary
- Optionally, specify a custom command if you use a specific way to run Gemini CLI
Example: Direct binary path
Example: Direct binary path
If you have Gemini CLI installed in a specific location:
Example: npm global install
Example: npm global install
If installed via npm globally:
Example: Homebrew install
Example: Homebrew install
If installed via Homebrew:
3
Enable Gemini CLI
Toggle “Enable” for Gemini CLI
Using Gemini CLI
Once enabled, Gemini CLI will appear in your model selection:1
Select Gemini CLI
In the cmd interface, open the model selector and choose “Gemini CLI”
2
Start Using
You can now use Gemini CLI’s advanced agentic capabilities:
- Multi-step task execution
- Integrates with your existing Gemini CLI configuration, including
GEMINI.md - Rich native UI in cmd

