NEWHow to check your Claude Code token spend  →
← Back to all agents
7.5
Shipyard Score
Good

What is it?

Gemini CLI is Google’s command-line interface that integrates Gemini into your terminal. Use it as a catch-all code generation, analysis, and debugging tool via prompting and chat-style workflows. If Gemini is your LLM of choice, Gemini CLI makes it more useful for programming tasks/workflows.

Gemini CLI terminal interface showing Google AI assistance for code generation and development workflow integration Gemini CLI responding to a refactoring prompt step-by-step

What can I use it for?

Like Claude Code, Gemini is really useful for any terminal-based ops (e.g. using devtools and running commands). Anything you’d normally do via terminal can be offloaded to Gemini, and it’ll ask your permission before taking steps on your behalf

  • Code generation: Write code to the correct files in response to user prompts
  • Code analysis: Review existing code for potential issues and optimizations
  • Debugging: Iterate on a solution while skimming logs until the correct output is reached
  • Documentation: Write docs for every new code change, knowing the full context of your feature
  • Learning: Ask questions about patterns, get answers customized to your codebase
  • Ops: Execute tasks from your command line

What we like about it

Gemini is often recognized as the strongest LLM for programming tasks, so this is a useful agentic wrapper that allows it to apply these decisions on your behalf. We like a terminal interface (since it stays out of the way and feels natural for most of our dev tasks), and Gemini’s is clean and intuitive.

Gemini CLI performing code analysis and debugging assistance with Google AI models in terminal environment Gemini CLI when given error logs and asked to resolve
Community

Chat with the Shipyard community on Slack.

Trade tips with other devs and DevOps teams, get help from our crew, and hear about events before they go live.

Join Slack →

Shipyard's Agentic Corner

Get better agentic workflows by instantly deploying to ephemeral environments.

Shipyard's environments are agent-friendly, so you can have a more continuous and productive agentic dev loop.

Stay connected

Latest Agents

Latest from the blog
Claude Code CLI cheatsheet with commands, configuration, and best practices

Claude Code CLI Cheatsheet: config, commands, prompts, + best practices

Get leet @ Anthropic's Claude Code with this cheatsheet, including config, CLI commands, advanced features, and best practices for faster dev + test.

Read the article →
Newsletter

Stay in the (inner) loop.

Hear about the latest and greatest in cloud native, agents, engineering, and more when you sign up for our monthly newsletter.