Gemini CLI
Gemini CLI is Google’s open-source AI agent for the terminal, giving direct access to Gemini models with built-in tools, MCP support and a generous free tier.
About this tool
Gemini CLI is an open-source command-line agent from Google that brings Gemini models directly into the terminal. Developers use it to explore and modify big codebases, build apps starting from screenshots or PDF files, and script multi-step workflows without leaving the command line. It is released under the Apache 2.0 licence.
The agent includes built-in tools for Google Search grounding, file operations, shell commands and web fetching, and supports the Model Context Protocol for custom integrations. An extensions gallery adds more capabilities. With a personal Google account, the free tier allows 60 requests per minute and 1,000 per day, using current Gemini models with a context window of up to one million tokens.
What you can do
Terminal-first agent
Work with Gemini directly from the command line to read, edit and generate code.
Built-in tools
Search grounding, file operations, shell commands and web fetching are available out of the box.
MCP and extensions
Connect custom tools through MCP and install extensions from a gallery.
Large context
Gemini models with up to a 1M-token context window handle large codebases.
Who is it for?
- A developer asks Gemini CLI to explain and refactor a module in a large repository.
- A designer turns a PDF mockup into a starter web app from the terminal.
- An engineer scripts a recurring maintenance workflow using shell tools.
Before you choose
The agent can run shell commands; review its proposed actions before approving them on important systems.
Free-tier limits apply per account; teams with heavy use may need paid API access.
Frequently asked questions
Is Gemini CLI free?
Yes. With a personal Google account, the free tier offers 60 requests per minute and 1,000 requests per day.
Is Gemini CLI open source?
Yes. Gemini CLI is open source under the Apache 2.0 licence and developed on GitHub by Google.
Can Gemini CLI use external tools?
Yes. It supports the Model Context Protocol for custom integrations and offers an extensions gallery.
Check the official website for current features, pricing, and terms.
Similar tools
Cline
CodingCline is a coding‑assistant that can edit source files, execute shell commands, browse the web for information, devise implementation plans, and track API usage costs, all through IDE and CLI integrations.
Google AI Studio
CodingGoogle AI Studio is Google’s web workspace for testing Gemini models, getting a Gemini API key, building prototypes and moving them into production.
Continue
CodingContinue was an open-source AI coding assistant for VS Code, JetBrains IDEs and the terminal. Cursor acquired the company, and the code remains available in a read-only repository.
Supermaven
CodingSupermaven is an AI code completion tool focused on speed, with a free tier and a Pro plan offering a 1-million-token context window for large codebases.
Freebuff
CodingFreebuff is a coding assistant that supports developers through multiple interaction modes, from executing code snippets to building complete applications.
Sourcegraph Cody
CodingSourcegraph Cody is an AI coding assistant for VS Code, JetBrains, Visual Studio, the web and the command line that draws context from Sourcegraph code search; it is supported on Sourcegraph Enterprise.