one year on
Google launches Gemini CLI, an open-source AI agent for the terminal
Google ships a free, open-source command-line AI agent with a massive free tier, aiming to lure developers away from Anthropic's Claude Code and OpenAI's Codex CLI.
Google today launched Gemini CLI, an open-source AI agent that brings the Gemini 2.5 Pro model directly into developers’ terminals. The tool, released under the Apache 2.0 license, is designed for coding, content generation, problem-solving, and task management. It offers what Google calls “the industry’s largest usage allowance”: 60 model requests per minute and 1,000 requests per day at no charge for personal Google account holders.
Gemini CLI integrates with the Model Context Protocol and can be extended with custom prompts and bundled extensions. It also shares underlying technology with Gemini Code Assist, Google’s IDE-based coding assistant, which now includes an agent mode in VS Code available on all plans. For professional developers requiring higher throughput, Google offers usage-based billing through AI Studio or Vertex AI keys.
The move positions Google squarely against Anthropic’s Claude Code and OpenAI’s Codex CLI, both of which have become popular terminal-based coding agents. By offering generous free access and open-sourcing the tool, Google aims to build a community around its AI models and accelerate adoption among developers who have increasingly turned to third-party tools like Cursor and GitHub Copilot.
The record
One year later — open only if you can handle spoilers
Gemini CLI rapidly gained adoption among open-source enthusiasts and hobbyists, though professional teams often found the free tier sufficient for moderate use. By mid-2026, Google had merged Gemini CLI's capabilities into a unified 'Google Developer AI' platform, while competitors continued to iterate on their own CLI agents.