跳到主要内容
Supermarket
返回能力市场
MCP Server
programming
Apache-2.0

gemini-cli

An open-source AI agent that brings the power of Gemini directly into your terminal.

google-geminigoogle-gemini
59/ 100

公开评测 · 综合采用结论

存在需要人工复核的风险或证据不足

查看评测依据 查找我项目的报告基于公开项目证据,非安全认证或安装推荐
108.9kstars
15.0kforks
最近更新 9小时前
评测生成时间(北京时间)
本报告引擎
v3.9.0
当前引擎
v3.17.3

本报告与当前引擎使用不同规则;原分数不会自动更新,不同版本的分数不宜直接对比。

重新评测此项目

进入后确认来源与额度,提交才会创建任务。

代码版本未记录或记录无效,无法核对本报告的 commit 与送评文本;不会用当前项目代码回填历史记录。

Evaluation report

综合采用结论

59
D
满分 100 · 静态采用参考
谨慎采用高风险
决策摘要

存在需要人工复核的风险或证据不足

92%
高置信度
100
文档
78
安全
89
质量
100
活跃
70
采用
  • 基础评测完成+25/25确定性评分与静态安全扫描已完成
  • README 有效证据+25/2512,093 个去重后的有效字符
  • 独立证据来源+12/203 类非重复证据,重复文件不叠加
  • 仓库元数据+10/10已取得仓库状态与采用数据
  • 活跃记录+5/5已取得最近提交时间
  • AI 复核+15/15已完成结构化 AI 证据复核

本报告评了什么

综合分用于静态采用筛选,不是任务成功率,也不代表使用 Skill 后的能力提升。

静态检查范围
记录 3 个文件 · 22,096 字符
只检查采集到的受限文本与已知风险模式;未读取的脚本、依赖和运行环境不在结论内。
AI 内容复核
已使用
复核送评文本的说明和设计,不是安装测试或实际任务执行。记录缺失时不推断已使用或未使用。
真实任务效果
本报告未提供实测证据
没有使用/不使用 Skill 的任务对照、重复运行或耗时与 token 成本结果。采用前仍需在隔离环境验证自己的任务。

脚本引用覆盖

脚本引用覆盖记录不可得;不推断没有引用或已经检查。

How it works · 时序图

Gemini CLI 认证与请求流程

README 描述了用户通过 CLI 发起请求,CLI 进行认证(OAuth 或 API Key)后调用 Gemini 模型,并返回结果的过程,涉及用户、CLI、认证服务、模型等多个参与方,存在请求和响应。

AI 提取 · 证据约束

左右滑动查看完整图示

Gemini CLI 认证与请求流程README 描述了用户通过 CLI 发起请求,CLI 进行认证(OAuth 或 API Key)后调用 Gemini 模型,并返回结果的过程,涉及用户、CLI、认证服务、模型等多个参与方,存在请求和响应。用户发起者Gemini CLI代理认证服务验证Gemini 模型处理输入命令认证请求认证结果API 请求响应输出结果
图示依据
  • • 认证选项章节:描述 Sign in with Google 和 API Key 流程
  • • 基本用法:gemini -p 命令示例
  • • 非交互模式:--output-format json 获取结构化输出
五维表现
Gemini CLI 作为终端 AI 代理,解决开发者命令行内获取 AI 能力的明确需求,提供多种安装方式、认证选项和丰富的功能示例,价值可验证。文档结构清晰,覆盖安装、使用、配置、安全等,但部分高级功能依赖外部文档,且错误处理细节未在 README 中直接展示。
质量证据
  • 安装章节:提供 npx、npm、Homebrew、MacPorts、Anaconda 安装命令
  • 认证选项:三种认证方式及环境变量设置(GEMINI_API_KEY、GOOGLE_API_KEY 等)
  • 基本用法:gemini -p 命令及 --output-format json/stream-json 示例
  • 文档导航:列出 Quickstart、Authentication、Configuration 等章节链接
  • 许可证:Apache 2.0 在 README 中明确标注
采用建议
优势
  • 问题与用途描述
  • 有效 README
  • 安装或接入步骤
  • 可执行示例
  • 提供多种安装方式(npx、npm、Homebrew、MacPorts、Anaconda)
关注点
  • 发现高风险的一键下载执行或安装命令
  • 错误处理细节未在 README 中直接展示,需依赖外部文档
  • 高级功能(如 MCP 配置、沙箱)仅提供链接,未在 README 中展开
  • 未明确说明不支持的功能或限制
  • 部分命令参数(如 --include-directories)未详细说明
适合

开发者希望在终端中快速使用 Gemini 模型、需要自动化脚本中调用 AI 的场景(headless 模式)、需要与 GitHub 工作流集成的团队、需要 MCP 扩展能力的用户

不建议直接用于

需要完全离线运行的场景(未提及离线支持)、对数据隐私要求极高且不允许外部 API 调用的环境(依赖 Google 服务)

也有自己的公开项目?先免登录查已有报告;没有报告时,可保留地址继续登录评测。

查找我项目的报告 →
文档证据
100/100
问题与用途描述10 分
有效 README12 分
安装或接入步骤14 分
可执行示例16 分
输入、参数或工具说明11 分
输出或结果说明9 分
限制、权限或边界12 分
错误处理或排障8 分
许可证信息5 分
结构化章节3 分
安全证据
高风险
发现高风险的一键下载执行或安装命令
unsafe-install-commandpackages/core/src/skills/builtin/antigravity-support/SKILL.md:41high confidence
curl -fsSL https://antigravity.google/cli/install.sh | bash

修复:固定版本与校验和,先下载审查再执行,避免管道直接交给 Shell。

优先改进清单
  1. 01固定版本与校验和,先下载审查再执行,避免管道直接交给 Shell。
方法、证据与局限展开
数据来源

GitHub Repository API

扫描范围

3 个文件 · 22,096 字符

评测引擎

v3.9.0 · AI 内容复核:已使用(deepseek-chat)

局限
  • 静态评测不会安装或执行项目代码
  • 安全扫描基于高信号文件与已知模式,不能替代人工审计
  • 流行度只反映采用程度,不代表安全或工程质量

30 天热度趋势

README

Gemini CLI

Gemini CLI CI Gemini CLI E2E (Chained) Version License View Code Wiki

[!IMPORTANT] Read before installing — Gemini CLI status & tool guide

  • Enterprise Code Assist only: Designed for Gemini Code Assist Standard / Enterprise licenses and Code Assist for GitHub on Google Cloud (your access remains unchanged).
  • No free tier or Google AI plans: Free individual access and Google AI Pro / Ultra (Google One) moved to Antigravity CLI on June 18, 2026 (transition post).
  • Not optimized for Gemini 4+: Not tuned for the Gemini 4 series (for example, Gemini 4 Argon) or future releases in this or later generations.
  • Not for model benchmarks: Don't use Gemini CLI to benchmark Gemini models—its harness isn't tuned for Gemini 4+ and produces unrepresentative scores.

Which Google CLI do you need?

ToolBest forLinks
Antigravity CLI (agy)Interactive multi-agent coding terminal. Use for Gemini 4 Argon+, free / Google AI Pro & Ultra accounts, or Google Cloud.Download · Migrate · Argon post
Gemini API CLI (gemini-api)Stateless API CLI (not a coding harness). Gives agents (agy, Claude Code, Codex), scripts, and CI direct commands for Gemini models, media gen, file analysis, and managed agents.GitHub · Releases · API docs
Gemini CLI (gemini, this repo)Organizations with Gemini Code Assist Standard / Enterprise or Code Assist for GitHub on Google Cloud (plus legacy paid API / Vertex keys).Docs

Gemini CLI (gemini) is an open-source terminal agent maintained for enterprise Gemini Code Assist workflows on Google Cloud. Learn more in the Gemini CLI documentation.

📦 Installation

See Gemini CLI installation, execution, and releases for recommended system specifications and a detailed installation guide.

Quick Install

Run instantly with npx

# Using npx (no installation required)
npx @google/gemini-cli

Install globally with npm

npm install -g @google/gemini-cli

Install globally with Homebrew (macOS/Linux)

brew install gemini-cli

Install globally with MacPorts (macOS)

sudo port install gemini-cli

Install with Anaconda (for restricted environments)

# Create and activate a new environment
conda create -y -n gemini_env -c conda-forge nodejs
conda activate gemini_env

# Install Gemini CLI globally via npm (inside the environment)
npm install -g @google/gemini-cli

Release Channels

See Releases for more details.

Preview

New preview releases will be published each week at UTC 23:59 on Tuesdays. These releases will not have been fully vetted and may contain regressions or other outstanding issues. Please help us test and install with preview tag.

npm install -g @google/gemini-cli@preview

Stable

  • New stable releases will be published each week at UTC 20:00 on Tuesdays, this will be the full promotion of last week's preview release + any bug fixes and validations. Use latest tag.
npm install -g @google/gemini-cli@latest

Nightly

  • New releases will be published each day at UTC 00:00. This will be all changes from the main branch as represented at time of release. It should be assumed there are pending validations and issues. Use nightly tag.
npm install -g @google/gemini-cli@nightly

📋 Key Features

Code Understanding & Generation

  • Query and edit large codebases
  • Generate new apps from PDFs, images, or sketches using multimodal capabilities
  • Debug issues and troubleshoot with natural language

Automation & Integration

  • Automate operational tasks like querying pull requests or handling complex rebases
  • Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria
  • Run non-interactively in scripts for workflow automation

🔐 Authentication Options

Choose the authentication method that best fits your needs:

Option 1: Sign in with Google (OAuth login using your Google Account)

When using a paid Code Assist License from your organization, remember to set the Google Cloud Project

# Set your Google Cloud Project
export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
gemini

Option 2: Gemini API Key

✨ Best for: Developers who need specific model control or paid tier access

Benefits:

  • Model selection: Choose specific Gemini models
  • Usage-based billing: Upgrade for higher limits when needed
# Get your key from https://aistudio.google.com/apikey
export GEMINI_API_KEY="YOUR_API_KEY"
gemini

Option 3: Vertex AI

✨ Best for: Enterprise teams and production workloads

Benefits:

  • Enterprise features: Advanced security and compliance
  • Scalable: Higher rate limits with billing account
  • Integration: Works with existing Google Cloud infrastructure
# Get your key from Google Cloud Console
export GOOGLE_API_KEY="YOUR_API_KEY"
export GOOGLE_GENAI_USE_VERTEXAI=true
gemini

For Google Workspace accounts and other authentication methods, see the authentication guide.

🚀 Getting Started

Basic Usage

Start in current directory

gemini

Include multiple directories

gemini --include-directories ../lib,../docs

Use specific model

gemini -m gemini-2.5-flash

Non-interactive mode for scripts

Get a simple text response:

gemini -p "Explain the architecture of this codebase"

For more advanced scripting, including how to parse JSON and handle errors, use the --output-format json flag to get structured output:

gemini -p "Explain the architecture of this codebase" --output-format json

For real-time event streaming (useful for monitoring long-running operations), use --output-format stream-json to get newline-delimited JSON events:

gemini -p "Run tests and deploy" --output-format stream-json

Quick Examples

Start a new project

cd new-project/
gemini
> Write me a Discord bot that answers questions using a FAQ.md file I will provide

Analyze existing code

git clone https://github.com/google-gemini/gemini-cli
cd gemini-cli
gemini
> Give me a summary of all of the changes that went in yesterday

📚 Documentation

Getting Started

Core Features

Tools & Extensions

Advanced Topics

Troubleshooting & Support

  • Troubleshooting Guide - Common issues and solutions.
  • FAQ - Frequently asked questions.
  • Use /bug command to report issues directly from the CLI.

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 #dev channel
> @database Run a query to find inactive users

See the MCP Server Integration guide for setup instructions.

🤝 Contributing

We welcome contributions! Gemini CLI is fully open source (Apache 2.0), and we encourage the community to:

  • Report bugs and suggest features.
  • Improve documentation.
  • Submit code improvements.
  • Share your MCP servers and extensions.

See our Contributing Guide for development setup, coding standards, and how to submit pull requests.

Check our Official Roadmap for planned features and priorities.

📖 Resources

Uninstall

See the Uninstall Guide for removal instructions.

📄 Legal

Star History Rank


Built with ❤️ by Google and the open source community