On Wednesday, Google officially launched a new feature for its command-line AI system, Gemini CLI, allowing outside companies to integrate directly into the AI product. Called Gemini CLI Extensions, the feature is launching with extensions from Figma, Stripe, and other companies.
This announcement comes just two days after OpenAI’s launch of apps in ChatGPT, which also integrated third-party systems into an AI environment. However, while app access to ChatGPT is tightly curated, Gemini CLI extensions can be published with no endorsement or participation from Google. Available extensions will be hosted in public repositories on Github and installed manually by developers.
A senior staff engineer on the project, Taylor Mullen, told TechCrunch that an open ecosystem is vital. He stated that everything they are doing is grounded in a fair ecosystem that anyone can participate in.
The first available extension was for Google’s own Nanobanana image generator, which was posted to GitHub last week. Once installed, the extension allows users to generate images directly from the Gemini CLI terminal.
Launched in June, Gemini CLI has grown to over one million users, according to Google, with usage heavily skewed towards software developers. Notably, Gemini CLI is heavily used in the development and maintenance of its own codebase, a process closely overseen by product managers.
In an interview, Google’s senior director of product management for developer tools, Ryan J. Salva, told TechCrunch that the purpose of the new feature was to turn Gemini CLI into an extensibility platform, a conduit to other tools and instructions that come from elsewhere in your tool chain.