Google Launches Gemini CLI for Developers

Google has launched a new open-source AI agent that brings the coding, content generation, and research power of Gemini directly into developer terminals. Dubbed Gemini CLI, Google describes it as a "fundamental upgrade to your command-line experience," enabling developers to write and debug code using simple, natural language prompts.
"It offers lightweight access to Gemini, creating the most direct path from your prompt to our model," Google stated in the announcement. "While it's exceptional at coding, we designed Gemini CLI to do far more. It's a versatile, local utility suitable for a wide variety of tasks, including content creation, problem-solving, in-depth research, and managing your workflow."
Gemini CLI is powered by Google's Gemini 2.5 Pro reasoning model, which currently features a 1-million-token context window—the volume of information the AI can process at once. According to Google, the CLI agent integrates with Gemini Code Assist, includes built-in support for the Model Context Protocol (MCP) and Google Search, and allows developers to create images and video using its Veo and Imagen AI tools.
The Gemini CLI preview is available for developers starting today. It is currently free to use with a free Gemini Code Assist license linked to a personal Google account. This license grants users a quota of 60 model requests per minute and up to 1,000 requests per day, which Google claims is the "largest allowance" provided in the industry.
Google has not specified options for users who might exceed these limits or whether the AI agent will stay free after its full public release. This generous usage tier could give it a competitive advantage over other AI coding assistants like Anthropic's Claude, GitHub Copilot, or even Microsoft's AI chatbot built into Windows Terminal.
Related article
Google’s Genie world model now simulates real streets with Street View
Most of us have used Google Street View to show a friend our old neighborhood or dropped the little person icon into Paris to check if our hotel is in a trendy area. Now, imagine experiencing that with full immersion and interactivity—simulating the
Takeda partners with Insilico in $600M AI drug discovery deal
Takeda has partnered with Hong Kong-based Insilico Medicine to leverage artificial intelligence for early-stage drug discovery across its therapeutic portfolios.Specific therapeutic areas or disease targets were not disclosed. The partnership grants
Deltek Study: 91% of Firms Call AI Critical to Success
Deltek research reveals that while project firms anticipate higher profits, execution gaps currently limit the measurable impact of AI. Credit: Nitat Termmee/Getty ImagesAccording to Deltek’s Heather Larkin, leading firms are successfully linking dat
Related Special Topic Recommendations
Comments (0)
0/500

Google has launched a new open-source AI agent that brings the coding, content generation, and research power of Gemini directly into developer terminals. Dubbed Gemini CLI, Google describes it as a "fundamental upgrade to your command-line experience," enabling developers to write and debug code using simple, natural language prompts.
"It offers lightweight access to Gemini, creating the most direct path from your prompt to our model," Google stated in the announcement. "While it's exceptional at coding, we designed Gemini CLI to do far more. It's a versatile, local utility suitable for a wide variety of tasks, including content creation, problem-solving, in-depth research, and managing your workflow."
Gemini CLI is powered by Google's Gemini 2.5 Pro reasoning model, which currently features a 1-million-token context window—the volume of information the AI can process at once. According to Google, the CLI agent integrates with Gemini Code Assist, includes built-in support for the Model Context Protocol (MCP) and Google Search, and allows developers to create images and video using its Veo and Imagen AI tools.
The Gemini CLI preview is available for developers starting today. It is currently free to use with a free Gemini Code Assist license linked to a personal Google account. This license grants users a quota of 60 model requests per minute and up to 1,000 requests per day, which Google claims is the "largest allowance" provided in the industry.
Google has not specified options for users who might exceed these limits or whether the AI agent will stay free after its full public release. This generous usage tier could give it a competitive advantage over other AI coding assistants like Anthropic's Claude, GitHub Copilot, or even Microsoft's AI chatbot built into Windows Terminal.
Google’s Genie world model now simulates real streets with Street View
Most of us have used Google Street View to show a friend our old neighborhood or dropped the little person icon into Paris to check if our hotel is in a trendy area. Now, imagine experiencing that with full immersion and interactivity—simulating the
Takeda partners with Insilico in $600M AI drug discovery deal
Takeda has partnered with Hong Kong-based Insilico Medicine to leverage artificial intelligence for early-stage drug discovery across its therapeutic portfolios.Specific therapeutic areas or disease targets were not disclosed. The partnership grants
Deltek Study: 91% of Firms Call AI Critical to Success
Deltek research reveals that while project firms anticipate higher profits, execution gaps currently limit the measurable impact of AI. Credit: Nitat Termmee/Getty ImagesAccording to Deltek’s Heather Larkin, leading firms are successfully linking dat





Home






