Gemini CLI User Guide

Basic Introduction

Gemini CLI is an open-source command-line AI tool provided by Google, bringing the powerful capabilities of Gemini directly to your terminal. It offers a lightweight way to access Gemini, providing the most direct path from your prompt to the model. By configuring aitokencore, you can use the Gemini CLI service normally even under restricted network conditions.

🚀 Why Choose Gemini CLI?

🧠 Powerful Gemini 2.5 Pro: Access to a 1 million token context window

🔧 Built-in Tools: Basic Google Search, file operations, Shell commands, web scraping

🔌 Extensible: Supports MCP (Model Context Protocol) for custom integrations

💻 Terminal-First: Designed specifically for developers working in the command line

🛡️ Open Source: Licensed under Apache 2.0

📦 Installation Methods

Quick Install

Run instantly with npx (no installation required)

Install globally with npm

Install with Homebrew (macOS/Linux)

System Requirements

Node.js version 20 or higher

macOS, Linux, or Windows

Using a Relay (Proxy)

1. Set Environment Variables

Before using the relay, configure the following environment variables:

Note: You can also add these environment variables to .bashrc, .zshrc, or other shell configuration files so they are set automatically every time you launch the terminal.

🚀 Quick Start

Basic Usage

Launch in the current directory

Include multiple directories

Use a specific model

Non-interactive script mode

Get a simple text response:

Get structured JSON output:

Quick Examples

Start a new project

Analyze existing code

📋 Main Features

Code Understanding & Generation

Query and edit large codebases

Generate new apps from PDFs, images, or sketches using multimodal capabilities

Debug issues and troubleshoot using natural language

Automation & Integration

Automate operational tasks such as reviewing pull requests or handling complex rebases

Connect new features using MCP servers

Run non-interactively in scripts for workflow automation

Advanced Features

Get real-time information using built-in Google Search

Conversation checkpoints to save and restore complex sessions

Custom context files (GEMINI.md) to tailor behavior for your project

Common Commands & Feature Examples

Explore a codebase

> Describe the main components of this system architecture
> What security mechanisms are in place?
> Provide a step-by-step onboarding document for new developers

Work with existing code

> Implement a draft for GitHub issue #123
> Help me migrate this codebase to the latest version of Java. First create a plan

Automate workflows

> Create a slideshow showing the past 7 days of git history, grouped by feature and team member
> Create a fullscreen web app for wall display showing our most active GitHub issues

System interaction

> Convert all images in this directory to png and rename them using dates from exif data
> Organize my PDF invoices by month of expense

GitHub Integration

Integrate Gemini CLI directly into your GitHub workflows using the Gemini CLI GitHub Action:

Pull Request Review: Automated code reviews with contextual feedback and suggestions

Issue Triage: Automatically label and prioritize GitHub issues based on content analysis

On-Demand Help: Mention @gemini-cli in issues and pull requests for help debugging, explaining, or delegating tasks

Custom Workflows: Build automated, scheduled, and on-demand workflows tailored to your team’s needs

Troubleshooting

If you encounter issues during use, refer to the following:

Check if environment variables are set correctly:

Check for stable network connectivity and accessibility of the relay:

Review any error output, which usually indicates the source of the problem

If using a SOCKS proxy, ensure the format is correct, e.g. socks5://<user>:<pass>@<proxy>:<port>

Report issues using the built-in command:

Release Notes

Preview

New preview versions are released every Tuesday at 23:59 UTC. Install using the preview tag:

Stable

New stable versions are released every Tuesday at 20:00 UTC. Install using the latest tag:

Nightly

Nightly versions are released daily at 00:00 UTC. Install using the nightly tag:

Using MCP Servers

Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools:

> @github list my open pull requests
> @slack send a summary of today's commits to the #dev channel
> @database run a query to find inactive users

Official Roadmap: View upcoming features

NPM Package: Package registry

GitHub Issues: Report bugs or request features

Security Advisories: Security updates

Uninstallation

If you need to uninstall Gemini CLI, refer to the official uninstallation guide.

Gemini CLI aitokencore Configuration and Usage Tutorial

Gemini CLI User Guide#

Basic Introduction#

🚀 Why Choose Gemini CLI?#

📦 Installation Methods#

Quick Install#

Run instantly with npx (no installation required)#

Install globally with npm#

Install with Homebrew (macOS/Linux)#

System Requirements#

Using a Relay (Proxy)#

1. Set Environment Variables#

🚀 Quick Start#

Basic Usage#

Launch in the current directory#

Include multiple directories#

Use a specific model#

Non-interactive script mode#

Quick Examples#

Start a new project#

Analyze existing code#

📋 Main Features#

Code Understanding & Generation#

Automation & Integration#

Advanced Features#

Common Commands & Feature Examples#

Explore a codebase#

Work with existing code#

Automate workflows#

System interaction#

GitHub Integration#

Troubleshooting#

Release Notes#

Preview#

Stable#

Nightly#

Using MCP Servers#

📚 Related Resources#

Uninstallation#