Gemini CLI — Getting Started (Enterprise)

Gemini CLI is Google's enterprise terminal-based AI coding agent for Vertex AI customers, with a 1M+ token context window. It runs current Gemini models such as Gemini 3.1 Pro and Gemini 3.8 Flash, integrates with Google's ecosystem (Drive, Gmail, Calendar), and supports opt-in sandboxed execution. Note that Gemini CLI has been deprecated for individual consumers in favor of Google Antigravity.

Enterprise Installation

Gemini CLI is available to Vertex AI customers. Contact your Google Cloud account team for access.

# Via npm (enterprise only)
npm install -g @google/gemini-cli

# Verify
gemini --version

Authentication (Vertex AI)

Enterprise authentication can use user Application Default Credentials locally or a service account key in CI/CD. Vertex AI requests require both a project and a location.

User ADC (local):

# Authenticate as a user via Google Cloud
gcloud auth application-default login

# Point Gemini CLI at Vertex AI
export GOOGLE_GENAI_USE_VERTEXAI=true
export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
export GOOGLE_CLOUD_LOCATION="YOUR_LOCATION"

# Verify in a session
gemini
> /auth

Service account (CI/CD):

export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
export GOOGLE_GENAI_USE_VERTEXAI=true
export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
export GOOGLE_CLOUD_LOCATION="YOUR_LOCATION"

Sandboxing

Sandboxing is opt-in. Enable it with -s / --sandbox, GEMINI_SANDBOX, or tools.sandbox in settings.json; set tools.sandbox to true or to a provider name:

{
  "tools": {
    "sandbox": "docker"
  }
}

Enable it per run with gemini -s, set GEMINI_SANDBOX=docker, or keep the tools.sandbox setting shown above. There are no workspace, read-only, isolated, or full sandbox modes.

First Session

cd my-project
gemini

First-start experience:

⚡ Welcome to Gemini CLI
  Model: gemini-3.1-pro-preview
  Context: 1,048,576 tokens
  Sandbox: disabled (use -s to enable)
  
  Type /help for commands.
  
>

Essential Slash Commands

Project Configuration: GEMINI.md

Create GEMINI.md (or .gemini/GEMINI.md) at project root:

# GEMINI.md

## Commands
- `npm run dev` — Start dev server
- `npm run build` — Production build
- `npm run test` — Vitest test suite
- `npm run lint` — ESLint + TypeScript

## Architecture
- Vite + React 19 with React Router v7
- Zustand for client state, React Query for server state
- Tailwind CSS v4 with custom design tokens

## Execution Rules
- Use `gemini -s` for untrusted or exploratory tasks
- Do not modify node_modules/, .env, or dist/
- Keep generated files inside src/, lib/, tests/, or public/

## Google Integration
- Google Drive folder: team/docs/shared — read only
- Google Calendar: check before scheduling changes

Google Ecosystem Integration

Gemini CLI connects to Google services through extensions. Browse the extensions gallery and install the ones you need:

# Install a Workspace extension
gemini extensions install <extension-name>

# List installed extensions
gemini extensions list

Then in prompts:

> Read the design spec from Google Drive (team/docs/specs/v2.md) 
  and compare it with our current implementation in src/components/.
  List gaps.

Context Window Advantage

With 1M tokens, Gemini CLI can hold your entire codebase in context. Use this for:

• Full codebase analysis — "Find every place we use localStorage and assess whether it should be sessionStorage"
• Cross-cutting refactors — "Rename User to Account across the entire codebase and update all references"
• Documentation generation — "Read every API route and generate OpenAPI specs"

Related Pages

• Prompt Engineering in Gemini CLI — extensions, prompt patterns, and context strategy
• Gemini CLI Configuration — settings.json, MCP, and .gemini/ conventions
• Tool Comparison — Gemini CLI vs Claude Code vs OpenCode vs Cursor vs Copilot
• Mastering Gemini CLI (Blog) — Comprehensive Gemini CLI guide with sandboxing and CI/CD

Sources

• Gemini CLI authentication
• Gemini CLI sandboxing
• Gemini CLI commands
• Gemini CLI configuration