Google has introduced Gemini CLI, a free, open-source AI tool designed to work directly in the developer’s terminal. The company says it wants to bring the power of Gemini into the hands of coders in the most native way possible: through the command line.
“We’re introducing Gemini CLI, an open-source AI agent that brings the power of Gemini directly into your terminal,” Google’s Taylor Mullen and Ryan J. Salva wrote in a blog post.
The Gemini CLI is powered by the Gemini 2.5 Pro model, which features an impressive 1 million-token context window, allowing for the easy analysis of large codebases or documents. It’s all built under the Apache 2.0 license, meaning developers can freely inspect, modify, or extend the software.
The tool can read files, execute commands, edit scripts, and even invoke Google Search results in real time to assist with context-sensitive tasks. For those who prefer hands-on control, the agent is extensible via the Model Context Protocol (MCP) and can integrate with external tools and data sources.
High usage limits, no cost for individuals
Google says it’s offering “unmatched usage limits for individual developers.” By logging in with a personal Google account, developers gain access to Gemini 2.5 Pro and can make up to 60 model requests per minute and 1,000 requests per day at no additional cost.
For professionals who require more, Google allows integration with AI Studio or Vertex AI for usage-based billing, or through Gemini Code Assist Standard and Enterprise licenses.
As the Google blog explains: “To ensure you rarely, if ever, hit a limit during this preview, we offer the industry’s largest allowance.”
The tech giant is also encouraging developers to contribute to the project on GitHub, where they can report bugs, suggest features, and submit code improvements.
A week of Gemini everywhere
Gemini CLI’s release comes amid a flurry of Gemini-powered announcements.
Over the past several months, Google has been steadily integrating Gemini features across its suite of apps, transforming tools into intelligent assistants. In Gmail, Docs, and Drive, Gemini now helps users draft emails, summarize documents, and organize files, all within the apps they already use.
Earlier this week, Google DeepMind announced Gemini Robotics On-Device, a new version of its model that runs locally on robots. It enables quick and intelligent task execution without needing cloud access.
On the hardware front, Lenovo launched the Chromebook Plus 14, which comes equipped with on-device Gemini AI, making everyday productivity smarter and entirely AI-assisted.
Want to incorporate AI into your workflow? Check out our list of the best free AI tools you can use right now.