gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
Top Related Projects
The official Python library for the OpenAI API
Integrate cutting-edge LLM technology quickly and easily into your apps
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
🦜🔗 The platform for reliable agents.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Quick Overview
Gemini-CLI is a command-line interface tool for interacting with Google's Gemini AI model. It allows users to access Gemini's capabilities directly from the terminal, enabling quick queries, text generation, and other AI-powered tasks without the need for a graphical interface or complex setup.
Pros
- Easy to use and integrate into existing command-line workflows
- Provides quick access to Gemini AI capabilities without leaving the terminal
- Lightweight and doesn't require extensive system resources
- Potential for scripting and automation of AI-powered tasks
Cons
- Limited to text-based interactions, lacking visual or graphical output
- May require API key management and potential usage costs
- Could have a learning curve for users not familiar with CLI tools
- Possibly limited in advanced features compared to full SDK or web interface
Code Examples
# Simple query to Gemini
gemini-cli ask "What is the capital of France?"
# Generate a short story
gemini-cli generate "Write a 100-word story about a time traveler"
# Analyze sentiment of a given text
gemini-cli analyze "I love using this CLI tool for AI tasks!"
Getting Started
-
Install Gemini-CLI:
pip install gemini-cli -
Set up your API key:
export GEMINI_API_KEY=your_api_key_here -
Run your first query:
gemini-cli ask "Hello, Gemini! How are you today?"
Competitor Comparisons
The official Python library for the OpenAI API
Pros of openai-python
- More comprehensive API coverage for OpenAI services
- Better documentation and examples
- Larger community and more frequent updates
Cons of openai-python
- Specific to OpenAI, not usable with other AI providers
- More complex setup and configuration required
Code Comparison
openai-python:
import openai
openai.api_key = "your-api-key"
response = openai.Completion.create(
engine="davinci",
prompt="Translate the following English text to French: '{}'",
max_tokens=60
)
gemini-cli:
from gemini import Gemini
gemini = Gemini(api_key="your-api-key")
response = gemini.generate_content(
"Translate the following English text to French: '{}'"
)
The openai-python library offers a more extensive API with various models and parameters, while gemini-cli provides a simpler interface focused on Gemini's capabilities. openai-python requires more setup but offers greater flexibility, whereas gemini-cli is more straightforward for quick interactions with Gemini models.
Integrate cutting-edge LLM technology quickly and easily into your apps
Pros of Semantic Kernel
- More comprehensive framework for building AI applications
- Supports multiple programming languages (C#, Python, Java)
- Extensive documentation and examples available
Cons of Semantic Kernel
- Steeper learning curve due to its complexity
- Requires more setup and configuration
- May be overkill for simple AI integrations
Code Comparison
Semantic Kernel (C#):
using Microsoft.SemanticKernel;
var kernel = Kernel.Builder.Build();
var result = await kernel.RunAsync("What is the capital of France?");
Console.WriteLine(result);
Gemini CLI (Python):
from gemini_cli import Gemini
gemini = Gemini()
response = gemini.generate_content("What is the capital of France?")
print(response.text)
Key Differences
- Semantic Kernel offers a more structured approach to building AI applications
- Gemini CLI provides a simpler, command-line focused interface
- Semantic Kernel supports multiple AI models, while Gemini CLI is specific to Google's Gemini model
- Semantic Kernel has a larger community and more extensive ecosystem
- Gemini CLI is more lightweight and easier to get started with for basic tasks
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Pros of transformers
- Extensive library supporting a wide range of models and tasks
- Well-documented with a large community and ecosystem
- Seamless integration with PyTorch and TensorFlow
Cons of transformers
- Steeper learning curve due to its comprehensive nature
- Potentially higher resource requirements for some models
Code Comparison
transformers:
from transformers import pipeline
classifier = pipeline("sentiment-analysis")
result = classifier("I love this product!")[0]
print(f"Label: {result['label']}, Score: {result['score']:.4f}")
gemini-cli:
from gemini import Gemini
gemini = Gemini()
response = gemini.generate_content("Analyze the sentiment: I love this product!")
print(response.text)
Key Differences
- transformers offers a broader range of pre-trained models and tasks
- gemini-cli focuses specifically on Google's Gemini model
- transformers provides more fine-grained control over model parameters
- gemini-cli aims for simplicity and ease of use with Google's API
Use Cases
- transformers: Ideal for researchers and developers working with various NLP tasks and models
- gemini-cli: Best for quick prototyping and leveraging Google's Gemini model capabilities
Community and Support
- transformers: Large, active community with extensive documentation and third-party resources
- gemini-cli: Newer project with growing community, backed by Google's support
🦜🔗 The platform for reliable agents.
Pros of LangChain
- More comprehensive framework for building LLM applications
- Supports multiple LLM providers and integrations
- Extensive documentation and active community support
Cons of LangChain
- Steeper learning curve due to its broader scope
- May be overkill for simple CLI applications
- Requires more setup and configuration
Code Comparison
LangChain example:
from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate
llm = OpenAI(temperature=0.9)
prompt = PromptTemplate(
input_variables=["product"],
template="What is a good name for a company that makes {product}?",
)
Gemini CLI example:
import gemini
model = gemini.load_model("gemini-pro")
response = model.generate_content("What is a good name for a company that makes shoes?")
print(response.text)
The LangChain example demonstrates its flexibility with prompt templates and different LLM providers, while the Gemini CLI example shows a more straightforward approach for quick interactions with the Gemini model. LangChain offers more customization options, but Gemini CLI provides a simpler interface for specific Gemini model interactions.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Pros of Haystack
- More comprehensive NLP framework with broader capabilities
- Extensive documentation and community support
- Modular architecture allowing for customization and flexibility
Cons of Haystack
- Steeper learning curve due to its complexity
- Potentially overkill for simple CLI applications
- Requires more setup and configuration
Code Comparison
Haystack example:
from haystack import Pipeline
from haystack.nodes import TextConverter, Preprocessor, FARMReader
pipeline = Pipeline()
pipeline.add_node(TextConverter(), name="TextConverter")
pipeline.add_node(Preprocessor(), name="Preprocessor")
pipeline.add_node(FARMReader(model_name_or_path="deepset/roberta-base-squad2"), name="Reader")
Gemini CLI example:
import gemini
model = gemini.load_model("gemini-pro")
response = model.generate_content("Tell me about the solar system")
print(response.text)
While Haystack offers a more complex pipeline for advanced NLP tasks, Gemini CLI provides a simpler interface for quick content generation using Google's Gemini model. Haystack is better suited for building comprehensive NLP applications, while Gemini CLI is ideal for rapid prototyping and simple AI-powered CLI tools.
Convert 
designs to code with AI
Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.
Try Visual CopilotREADME
Gemini CLI
Gemini CLI is an open-source AI agent that brings the power of Gemini directly into your terminal. It provides lightweight access to Gemini, giving you the most direct path from your prompt to our model.
ð Why Gemini CLI?
- ð¯ Free tier: 60 requests/min and 1,000 requests/day with personal Google account.
- ð§ Powerful Gemini 2.5 Pro: Access to 1M token context window.
- ð§ Built-in tools: Google Search grounding, file operations, shell commands, web fetching.
- ð Extensible: MCP (Model Context Protocol) support for custom integrations.
- ð» Terminal-first: Designed for developers who live in the command line.
- ð¡ï¸ Open source: Apache 2.0 licensed.
ð¦ Installation
Quick Install
Run instantly with npx
# Using npx (no installation required)
npx https://github.com/google-gemini/gemini-cli
Install globally with npm
npm install -g @google/gemini-cli
Install globally with Homebrew (macOS/Linux)
brew install gemini-cli
System Requirements
- Node.js version 20 or higher
- macOS, Linux, or Windows
Release Cadence and Tags
See Releases for more details.
Preview
New preview releases will be published each week at UTC 2359 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 2000 on Tuesdays, this will be the full promotion of last week's
previewrelease + any bug fixes and validations. Uselatesttag.
npm install -g @google/gemini-cli@latest
Nightly
- New releases will be published each week at UTC 0000 each day, 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
nightlytag.
npm install -g @google/gemini-cli@nightly
ð 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
Advanced Capabilities
- Ground your queries with built-in Google Search for real-time information
- Conversation checkpointing to save and resume complex sessions
- Custom context files (GEMINI.md) to tailor behavior for your projects
GitHub Integration
Integrate Gemini CLI directly into your GitHub workflows with Gemini CLI GitHub Action:
- Pull Request Reviews: Automated code review with contextual feedback and suggestions
- Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis
- On-demand Assistance: Mention
@gemini-cliin issues and pull requests for help with debugging, explanations, or task delegation - Custom Workflows: Build automated, scheduled and on-demand workflows tailored to your team's needs
ð Authentication Options
Choose the authentication method that best fits your needs:
Option 1: Login with Google (OAuth login using your Google Account)
⨠Best for: Individual developers as well as anyone who has a Gemini Code Assist License. (see quota limits and terms of service for details)
Benefits:
- Free tier: 60 requests/min and 1,000 requests/day
- Gemini 2.5 Pro with 1M token context window
- No API key management - just sign in with your Google account
- Automatic updates to latest models
Start Gemini CLI, then choose Login with Google and follow the browser authentication flow when prompted
gemini
If you are 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:
- Free tier: 100 requests/day with Gemini 2.5 Pro
- 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.
ð 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
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
ð Documentation
Getting Started
- Quickstart Guide - Get up and running quickly.
- Authentication Setup - Detailed auth configuration.
- Configuration Guide - Settings and customization.
- Keyboard Shortcuts - Productivity tips.
Core Features
- Commands Reference - All slash commands (
/help,/chat, etc). - Custom Commands - Create your own reusable commands.
- Context Files (GEMINI.md) - Provide persistent context to Gemini CLI.
- Checkpointing - Save and resume conversations.
- Token Caching - Optimize token usage.
Tools & Extensions
- Built-in Tools Overview
- MCP Server Integration - Extend with custom tools.
- Custom Extensions - Build and share your own commands.
Advanced Topics
- Headless Mode (Scripting) - Use Gemini CLI in automated workflows.
- Architecture Overview - How Gemini CLI works.
- IDE Integration - VS Code companion.
- Sandboxing & Security - Safe execution environments.
- Trusted Folders - Control execution policies by folder.
- Enterprise Guide - Deploy and manage in a corporate environment.
- Telemetry & Monitoring - Usage tracking.
- Tools API Development - Create custom tools.
Troubleshooting & Support
- Troubleshooting Guide - Common issues and solutions.
- FAQ - Frequently asked questions.
- Use
/bugcommand 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.
ð¤ 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.
ð Resources
- Official Roadmap - See what's coming next.
- Changelog - See recent notable updates.
- NPM Package - Package registry.
- GitHub Issues - Report bugs or request features.
- Security Advisories - Security updates.
Uninstall
See the Uninstall Guide for removal instructions.
ð Legal
- License: Apache License 2.0
- Terms of Service: Terms & Privacy
- Security: Security Policy
Built with â¤ï¸ by Google and the open source community
Top Related Projects
The official Python library for the OpenAI API
Integrate cutting-edge LLM technology quickly and easily into your apps
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
🦜🔗 The platform for reliable agents.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Convert designs to code with AI
Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.
Try Visual Copilot