Google’s Gemini CLI is a new, open-source AI agent designed specifically for developers who prefer working directly in the command line interface (CLI). It brings the power of Google’s Gemini AI models—notably Gemini 2.5 Pro—into the terminal, offering natural language command execution, code generation, debugging, content creation, and more, all without leaving the CLI environment.
Key Features and Capabilities
Gemini CLI is released as open source under the Apache 2.0 license, allowing developers to inspect, modify, and extend its functionality. Most developers can use it for free by simply logging in with a personal Google account, which grants a Gemini Code Assist license. For free users, Gemini CLI offers 60 model requests per minute and up to 1,000 requests per day—limits that Google set intentionally above typical developer usage to avoid inhibiting creativity.
The CLI is tightly integrated with Google’s Gemini Code Assist, enabling AI-first coding experiences in both the terminal and VS Code. This integration means developers can leverage advanced AI features across their development environments.
Users get access to Gemini 2.5 Pro, which supports a massive 1 million token context window, enabling complex codebase analysis and manipulation. Beyond coding, Gemini CLI can be used for content generation, problem-solving, research, and task management. It also supports automation of operational tasks, such as querying pull requests or handling complex rebases. The tool can generate new applications from PDFs or sketches using Gemini’s multimodal features and connect to Google’s creative AI tools like Imagen (image generation) and Veo (video generation).
Gemini CLI works across Windows, macOS, and Linux, making it accessible to a wide range of developers.
How to Get Started
1. Prerequisites: Install Node.js (version 18 or higher).
2. Installation: Run npx https://github.com/google-gemini/gemini-cli or install globally with npm install -g @google/gemini-cli.
3. Authentication: Sign in with a personal Google account to activate the free license and usage limits.
4. Advanced Use: For higher request limits or specific models, use an API key from Google AI Studio or Vertex AI.
