Open-source coding agents
Gemini CLI on GitHub: what it does and how to use it with AI agents
Google's open-source agent that brings Gemini into your terminal.
Stars, license and last push from the GitHub API, checked 2026-10-26
| Repo | google-gemini/gemini-cli |
|---|---|
| Stars | 108,500+ |
| License | Apache-2.0 |
| Last push | 2026-10-26 |
| Language | TypeScript |
What Gemini CLI does
Gemini CLI is a terminal agent that can read and edit files, run shell commands, search the web and connect to MCP servers. It reads project instructions from a GEMINI.md file.
Who it is for
Developers who want a terminal agent on Google models, or a second agent to cross-check Claude Code or Codex.
How to use Gemini CLI with Claude Code, Codex or Cursor
Install: npm install -g @google/gemini-cliRun gemini in your project and sign in with a Google account or API key.Add a GEMINI.md with project rules.Add MCP servers in settings.json.
Tip: Check the README for current free usage limits before you plan a big job on it.
The loadout for this repo
See the full tool stack, prompts and costs in Best AI coding agent setup.
Related repos
- OpenAI Codex CLI: OpenAI's open-source coding agent that runs in your terminal.
- MCP Servers: The official reference servers for the Model Context Protocol.
Gemini CLI FAQ
Is Gemini CLI free?
The tool is open source under Apache-2.0. Model usage limits depend on how you sign in. Check the README.
Does Gemini CLI support MCP?
Yes. MCP servers are configured in its settings.json.
What file holds project instructions?
GEMINI.md in your project.
Star counts change daily. Always read a repo's license and code before running it. All repos