Gemini CLI
Published Updated
What is Gemini CLI?
Gemini CLI is Google’s open-source terminal agent that brings Gemini models and MCP tool support to the command line, where it can read a repository, edit files and run commands.
An open-source terminal interface from Google that brings the power of Gemini models and the Model Context Protocol (MCP) directly into the local command line.
The Gemini CLI provides a Read-Eval-Print Loop (REPL) environment to interact with Google's AI models. It acts as an agentic framework capable of performing file system operations, executing shell commands, and utilizing custom tools via MCP to orchestrate complex development workflows locally.
How it relates to Orbit
Orbit can register Gemini CLI as a coding harness and route a model tier to it. See Agent Sessions & Harnesses for details.
When you would use it
You use the Gemini CLI when you want an extensible, open-source terminal agent that specifically leverages Google's multimodal models and natively supports MCP integrations.
Common operations
- Querying and editing large codebases locally.
- Automating task planning and execution via subagents.
- Hooking up local databases to Gemini using MCP servers.
Frequently asked questions
Is Gemini CLI open source?
Yes, Google publishes it as open source, and it can be extended with MCP servers.
Can Orbit route prompts to Gemini CLI?
Yes. Gemini CLI registers as a coding harness and any complexity tier can be routed to it. See Agent Sessions & Harnesses.
Related terms
Where this is taught
No learning path uses this term yet. Browse the Learning Atlas for guided sequences through related ideas.