On Wednesday, Google officially released Gemini CLI, a new feature in its command-line AI system, allowing outside companies to integrate directly into their AI products. The feature, called Gemini CLI Extensions, will be released alongside extensions from Figma, Stripe, and other companies.
This announcement comes just two days after OpenAI released an app on ChatGPT that also integrated third-party systems into the AI environment. However, while app access to ChatGPT is strictly controlled, Gemini CLI extensions can be published without Google’s approval or participation. Available extensions are hosted in a public repository on GitHub and installed manually by developers.
“That open ecosystem is extremely important to us,” Taylor Mullen, a senior staff engineer on the project, told TechCrunch. “Everything we do is based on a fair ecosystem where everyone can participate.”
The first available extension is for Google’s own Nanobanana image generator, which was posted to GitHub last week. After installing this extension, users will be able to generate images directly from the Gemini CLI terminal.
Google says Gemini CLI, which was released in June, has more than 1 million users, with usage skewed heavily toward software developers. In particular, as detailed in a recent TechCrunch interview, the Gemini CLI is frequently used for developing and maintaining proprietary codebases that are closely supervised by product managers.
Ryan J. Salva, Google’s senior director of product management for developer tools, told TechCrunch in an interview that the goal of the new features is to turn the Gemini CLI into “an extensibility platform, a pipeline to other tools and instructions that come from elsewhere in the toolchain.”
