An open-source AI agent that brings the power of Gemini directly into your terminal.
About this project
gemini-cli is an open-source developer tooling project on GitHub: An open-source AI agent that brings the power of Gemini directly into your terminal. It is a developer tool rather than an end-user product: the kind of project that changes how code is written, reviewed or shipped. It is maintained by google-gemini and published as a public repository you can read, fork and run yourself.
On GitHub the repository is tagged ai, ai-agents, cli, gemini, gemini-api, mcp-client and mcp-server, which is a fair summary of what it covers. Expect a mix of editor integration, command-line workflows and automation hooks, so it slots into an existing repository instead of replacing the toolchain around it.
It is written mainly in TypeScript and released under APACHE-2.0, a permissive license — commercial use is fine as long as copyright notices are kept. It is actively maintained: the most recent commit landed on November 18, 2026.
To try it, clone the repository and follow its README; that file is the canonical install guide. There is also a project page at https://geminicli.com for documentation or a hosted demo. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.
Key facts as recorded on GitHub: 108,912 stars; 14,961 forks; primary language TypeScript; license APACHE-2.0; last commit on November 18, 2026; topics ai, ai-agents, cli, gemini, gemini-api, mcp-client.