En Español
IBL News | New York
Google introduced an open-source AI agent for developers called Gemini CLI this month.
It brings Gemini directly into the terminal for coding, problem-solving, deep research, video creation, and task management through prompts.
Developers can access Gemini 2.5 Pro (and its massive 1 million token context window) free of charge with a personal Google account, or use a Google AI Studio or Vertex AI key for more access. At no charge, it’s allowed 60 model requests per minute and 1,000 requests per day.`
Gemini CLI, now in preview, can be extended for the Model Context Protocol (MCP) or bundled extensions.
Because Gemini CLI is fully open source (Apache 2.0), developers can inspect the code to understand how it works and verify its security implications.
Google encourages developers to contribute to this project by reporting bugs, suggesting features, continually improving security practices, and submitting code improvements.
