Gemini CLI Chinese User Guide

Basic introduction

Gemini CLI is an open source command-line AI tool provided by Google that brings the power of Gemini directly to your terminal. It provides lightweight access to Gemini, giving you the most direct path from prompt to model. By setting up a relay (proxy), you can use the Gemini CLI service normally when the network is restricted.

🚀 Why choose Gemini CLI?

🧠 Powerful Gemini 2.5 Pro: access to 1 million token context windows

🔧 Built-in tools: basic Google search functions, file operations, Shell commands, web crawling

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

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

🛡️ Open Source: Apache 2.0 License

📦 Installation method

Quick installation

Run instantly using npx (no installation required)

Install globally using npm

Install using Homebrew (macOS/Linux)

System requirements

Node.js version 20 or higher

macOS, Linux or Windows

Configure the transfer station (agent) to use

1. Set environment variables

Before using the relay station, you need to configure the following environment variables:

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

🚀 Quick Start

Basic usage

Start in the current directory

Contains multiple directories

Use a specific model

Script non-interactive mode

Get a simple text response:

Get structured JSON output:

Quick example

Start a new project

Analyze existing code

📋 Main functions

Code understanding and generation

Query and edit large code bases

Use multimodal capabilities to generate new apps from PDFs, images or sketches

Debugging issues and troubleshooting using natural language

Automation and Integration

Automate operational tasks such as querying pull requests or handling complex rebasing operations

New features using MCP server connection

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 conversations

Custom context file (GEMINI.md) to customize behavior for your project

Common commands and function examples

Explore the code base

> Describe the main components of this system architecture
> What safety mechanisms are in place?
> Provide new developers with a step-by-step getting started document

Working with existing code

> Implement a first draft for GitHub issue #123
> Help me migrate this code base to the latest version of Java. Make a plan first

Automated workflow

> Make a slideshow showing the past 7 days of git history, grouped by feature and team member
> Make a full-screen web app for a wall display showcasing our most interactive 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 spending month

GitHub integration

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

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

Issue Classification: Automatically tag and prioritize GitHub issues based on content analysis

Help on demand: Mention @gemini-cli in issues and pull requests to get help with debugging, explanation, or task delegation

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

Troubleshooting

If you encounter problems during use, you can refer to the following points:

Check whether the environment variables are set correctly:

Check whether the network connection is stable and whether the transfer station is accessible:

Check if there is any error message output, these messages usually indicate the problem

If using SOCKS proxy, make sure the proxy format is correct, for example socks5://<user>:<pass>@<proxy>:<port>

Report a problem using built-in commands:

Release Notes

Preview

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

Stable version (Stable)

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

Nightly

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

MCP server usage

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

> @github lists my open pull requests
> @slack Send a summary of today's commit to the #dev channel
> @database runs a query to find inactive users

Official Roadmap: See upcoming features

NPM Packages: package registry

GitHub Issues: Report a bug or request a feature

Security Recommendation: Security Updates

Uninstall

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

Gemini CLI transfer station configuration and usage tutorial

Gemini CLI Chinese User Guide#

Basic introduction#

🚀 Why choose Gemini CLI?#

📦 Installation method#

Quick installation#

Run instantly using npx (no installation required)#

Install globally using npm#

Install using Homebrew (macOS/Linux)#

System requirements#

Configure the transfer station (agent) to use#

1. Set environment variables#

🚀 Quick Start#

Basic usage#

Start in the current directory#

Contains multiple directories#

Use a specific model#

Script non-interactive mode#

Quick example#

Start a new project#

Analyze existing code#

📋 Main functions#

Code understanding and generation#

Automation and Integration#

Advanced features#

Common commands and function examples#

Explore the code base#

Working with existing code#

Automated workflow#

System interaction#

GitHub integration#

Troubleshooting#

Release Notes#

Preview#

Stable version (Stable)#

Nightly#

MCP server usage#

📚 Related resources#

Uninstall#