🔗 Forked from Official Google Gemini CLI: https://github.com/google-gemini/gemini-cli
⭐ 致敬原作者: 本项目基于 Google 官方开源的 Gemini CLI 进行二次开发
📋 声明: 本项目为非官方增强版本,保持与上游项目的完全兼容性
Language | Link |
---|---|
English | English Version |
中文 | 中文版本 |
🚀 Enhanced Fork Version 🚀
🔗 Based on: Official Google Gemini CLI (Star ⭐ 65.9k)
This project is a fork of Google's official Gemini CLI with secondary development, fully retaining all original features while adding the following enhancements:
✨ New Features:
- 🌍 Native Proxy API Support - Custom API endpoints via
GEMINI_API_BASE_URL
environment variable- 🔀 Enhanced Proxy Functionality - Complete HTTP/HTTPS proxy support, including sandbox environment proxy
- 📦 Direct GitHub Installation - Install directly from GitHub repository without npm publishing
- 🛡️ Network Security - Complete proxy script examples and network filtering functionality
- 🔧 Flexible Configuration - Support for various network environments and proxy configurations
🎯 Use Cases: Especially suitable for users who need to access Gemini API through proxy or relay services
This repository contains the Gemini CLI, a command-line AI workflow tool that connects to your tools, understands your code and accelerates your workflows.
With the Gemini CLI you can:
- Query and edit large codebases in and beyond Gemini's 1M token context window.
- Generate new apps from PDFs or sketches, using Gemini's multimodal capabilities.
- Automate operational tasks, like querying pull requests or handling complex rebases.
- Use tools and MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria
- Ground your queries with the Google Search tool, built into Gemini.
You have two options to install Gemini CLI.
-
Prerequisites: Ensure you have Node.js version 20 or higher installed.
-
Run the CLI: Execute the following command in your terminal:
npx https://github.com/aigo666/gemini-cli-new
Then, run the CLI from anywhere:
gemini
- Pick a color theme
- Authenticate: When prompted, sign in with your personal Google account. This will grant you up to 60 model requests per minute and 1,000 model requests per day using Gemini.
You are now ready to use the Gemini CLI!
🌟 This enhanced version supports proxy API access through custom endpoints
💡 Recommended Proxy Service: 极速API - Reliable Gemini API proxy service sponsor
The Gemini API provides a free tier with 100 requests per day using Gemini 2.5 Pro, control over which model you use, and access to higher rate limits (with a paid plan):
-
Generate a key from Google AI Studio.
-
Set it as an environment variable in your terminal. Replace
YOUR_API_KEY
with your generated key.✨ Standard Configuration (Direct):
export GEMINI_API_KEY="YOUR_API_KEY"
🌍 Proxy API Configuration (Recommended):
export GEMINI_API_KEY="YOUR_API_KEY" export GEMINI_API_BASE_URL="https://your-proxy-server.com" # Example with 极速API: export GEMINI_API_BASE_URL="https://api.jisuai.top" # Other examples: export GEMINI_API_BASE_URL="https://api.example.com/v1"
🔀 Advanced Proxy Configuration:
export GEMINI_API_KEY="YOUR_API_KEY" export GEMINI_API_BASE_URL="https://api.jisuai.top" # Using 极速API export HTTPS_PROXY="http://proxy.example.com:8080" export HTTP_PROXY="http://proxy.example.com:8080"
-
(Optionally) Upgrade your Gemini API project to a paid plan on the API key page (will automatically unlock Tier 1 rate limits)
Once the CLI is running, you can start interacting with Gemini from your shell.
You can start a project from a new directory:
cd new-project/
gemini
> Write me a Gemini Discord bot that answers questions using a FAQ.md file I will provide
Or work with an existing project:
git clone https://github.com/aigo666/gemini-cli-new
cd gemini-cli-new
gemini
> Give me a summary of all of the changes that went in yesterday
- Learn how to contribute to or build from the source.
- Explore the available CLI Commands.
- If you encounter any issues, review the troubleshooting guide.
- For more comprehensive documentation, see the full documentation.
- Take a look at some popular tasks for more inspiration.
- Check out our Official Roadmap
Head over to the troubleshooting guide if you're having issues.
Start by cd
ing into an existing or newly-cloned repository and running gemini
.
> Describe the main pieces of this system's architecture.
> What security mechanisms are in place?
> Provide a step-by-step dev onboarding doc for developers new to the codebase.
> Summarize this codebase and highlight the most interesting patterns or techniques I could learn from.
> Identify potential areas for improvement or refactoring in this codebase, highlighting parts that appear fragile, complex, or hard to maintain.
> Which parts of this codebase might be challenging to scale or debug?
> Generate a README section for the [module name] module explaining what it does and how to use it.
> What kind of error handling and logging strategies does the project use?
> Which tools, libraries, and dependencies are used in this project?
> Implement a first draft for GitHub issue #123.
> Help me migrate this codebase to the latest version of Java. Start with a plan.
Use MCP servers to integrate your local system tools with your enterprise collaboration suite.
> Make me a slide deck showing the git history from the last 7 days, grouped by feature and team member.
> Make a full-screen web app for a wall display to show our most interacted-with GitHub issues.
> Convert all the images in this directory to png, and rename them to use dates from the exif data.
> Organize my PDF invoices by month of expenditure.
Head over to the Uninstall guide for uninstallation instructions.
The core feature of this enhanced version is proxy API support, implemented through:
GEMINI_API_BASE_URL
Environment Variable: Set custom API endpoints (recommended: 极速API)- Proxy Support: Support for HTTP/HTTPS proxy servers
- Sandbox Proxy: Custom sandbox network proxy via
GEMINI_SANDBOX_PROXY_COMMAND
- Network Filtering: Domain whitelist and security filtering features
For detailed proxy configuration examples, refer to:
- 🐛 Issue Reports: Submit Issue
- 📚 Complete Documentation: View Docs
- 🚀 Contribute Code: Contribution Guide
✅ Fully Compatible: This version is fully compatible with the official Gemini CLI, all original features work normally ✅ Configuration Migration: Existing configuration files and settings can be used without modification ✅ Command Line Interface: All command line arguments and interaction methods remain consistent
For details on the terms of service and privacy notice applicable to your use of Gemini CLI, see the Terms of Service and Privacy Notice.
🚀 二开增强版本 🚀
🔗 基于项目: Google 官方 Gemini CLI (⭐ 65.9k Stars)
本项目是 Google 官方 Gemini CLI 的 Fork 版本,进行二次开发,完全保留原版所有功能的同时,新增以下特性:
✨ 新增特性:
- 🌍 原生中转API支持 - 通过
GEMINI_API_BASE_URL
环境变量支持自定义API端点- 🔀 增强代理功能 - 完整的HTTP/HTTPS代理支持,包括沙盒环境代理
- 📦 GitHub直装 - 支持直接从GitHub仓库安装,无需发布到npm
- 🛡️ 网络安全 - 提供完整的代理脚本示例和网络过滤功能
- 🔧 灵活配置 - 支持多种网络环境和代理配置方案
🎯 适用场景:特别适合需要通过代理或中转服务访问Gemini API的用户
本仓库包含 Gemini CLI,这是一个命令行AI工作流工具,能够连接到您的工具,理解您的代码并加速您的工作流程。
使用 Gemini CLI,您可以:
- 在 Gemini 的 1M token 上下文窗口内外查询和编辑大型代码库
- 使用 Gemini 的多模态功能从 PDF 或草图生成新应用
- 自动化操作任务,如查询拉取请求或处理复杂的变基操作
- 使用工具和 MCP 服务器连接新功能,包括使用 Imagen、Veo 或 Lyria 进行媒体生成
- 使用内置于 Gemini 的 Google 搜索工具来完善您的查询
您有两种安装 Gemini CLI 的选择。
-
前提条件: 确保您已安装 Node.js 版本 20 或更高版本。
-
运行 CLI: 在终端中执行以下命令:
npx https://github.com/aigo666/gemini-cli-new
然后,您可以从任何地方运行 CLI:
gemini
- 选择颜色主题
- 身份验证: 出现提示时,使用您的个人 Google 账户登录。这将为您提供每分钟最多 60 个模型请求和每天 1,000 个模型请求的使用量。
现在您已准备好使用 Gemini CLI!
🌟 本增强版本支持通过自定义端点进行中转API访问
💡 推荐中转服务商: 极速API - 可靠的Gemini API中转服务赞助商
Gemini API 提供免费套餐,使用 Gemini 2.5 Pro 可享受每天 100 个请求,控制使用的模型,并可访问更高的速率限制(通过付费计划):
-
从 Google AI Studio 生成密钥。
-
在终端中将其设置为环境变量。将
YOUR_API_KEY
替换为您生成的密钥。✨ 标准配置(直连):
export GEMINI_API_KEY="YOUR_API_KEY"
🌍 中转API配置(推荐):
export GEMINI_API_KEY="YOUR_API_KEY" export GEMINI_API_BASE_URL="https://your-proxy-server.com" # 推荐使用极速API:export GEMINI_API_BASE_URL="https://api.jisuai.top" # 其他示例:export GEMINI_API_BASE_URL="https://api.example.com/v1"
🔀 高级代理配置:
export GEMINI_API_KEY="YOUR_API_KEY" export GEMINI_API_BASE_URL="https://api.jisuai.top" # 使用极速API export HTTPS_PROXY="http://proxy.example.com:8080" export HTTP_PROXY="http://proxy.example.com:8080"
-
(可选)在 API 密钥页面将您的 Gemini API 项目升级到付费计划(将自动解锁第1层速率限制)
CLI 运行后,您可以开始从shell与 Gemini 交互。
您可以从新目录开始项目:
cd new-project/
gemini
> 为我编写一个 Gemini Discord 机器人,使用我将提供的 FAQ.md 文件回答问题
或者与现有项目一起工作:
git clone https://github.com/aigo666/gemini-cli-new
cd gemini-cli-new
gemini
> 给我一个昨天所有更改的摘要
如果您遇到问题,请前往故障排除指南。
首先 cd
到现有或新克隆的仓库,然后运行 gemini
。
> 描述此系统架构的主要组成部分。
> 有哪些安全机制?
> 为新加入此代码库的开发者提供逐步的开发入门文档。
> 总结此代码库并突出显示我可以学到的最有趣的模式或技术。
> 识别此代码库中潜在的改进或重构领域,突出显示看起来脆弱、复杂或难以维护的部分。
> 此代码库的哪些部分可能在扩展或调试时具有挑战性?
> 为 [模块名称] 模块生成 README 部分,解释它的作用和使用方法。
> 项目使用什么样的错误处理和日志记录策略?
> 此项目中使用了哪些工具、库和依赖项?
> 为 GitHub issue #123 实现初稿。
> 帮我将此代码库迁移到最新版本的 Java。先制定计划。
使用 MCP 服务器将您的本地系统工具与企业协作套件集成。
> 为我制作一个幻灯片演示,显示过去7天的git历史,按功能和团队成员分组。
> 制作一个全屏网络应用用于墙面显示,显示我们交互最多的 GitHub issues。
> 将此目录中的所有图像转换为 png,并使用 exif 数据中的日期重命名它们。
> 按支出月份整理我的PDF发票。
前往卸载指南获取卸载说明。
本增强版本的核心特性是支持中转API,通过以下方式实现:
GEMINI_API_BASE_URL
环境变量:设置自定义API端点(推荐:极速API)- 代理支持:支持HTTP/HTTPS代理服务器
- 沙盒代理:通过
GEMINI_SANDBOX_PROXY_COMMAND
自定义沙盒网络代理 - 网络过滤:提供域名白名单和安全过滤功能
详细的代理配置示例请参考:
✅ 完全兼容:本版本与官方Gemini CLI完全兼容,所有原有功能均可正常使用 ✅ 配置迁移:现有的配置文件和设置无需修改即可使用 ✅ 命令行接口:所有命令行参数和交互方式保持一致
有关适用于您使用 Gemini CLI 的服务条款和隐私声明的详细信息,请参阅服务条款和隐私声明。
本项目基于 Google 官方开源的 Gemini CLI 进行二次开发:
Original Project: https://github.com/google-gemini/gemini-cli
License: Apache-2.0
Authors: Google & Contributors
- ✅ 完全开源: 遵循原项目 Apache-2.0 开源协议
- ✅ 非官方版本: 本项目为社区维护的增强版本,非 Google 官方发布
- ✅ 上游兼容: 保持与官方版本的完全兼容性,可随时迁移回官方版本
- ✅ 功能增强: 在原有功能基础上新增中转API、代理支持等特性
欢迎向本项目贡献代码,同时也鼓励向官方项目贡献!
⚡ 快速链接 / Quick Links