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.
The announcement comes just two days after OpenAI’s launch of apps in ChatGPT, which also integrated third-party systems into an AI environment. But 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.
“That open ecosystem is vital to us,” Taylor Mullen, a senior staff engineer on the project, told TechCrunch. “Everything we’re doing is grounded in a fair ecosystem that anyone can participate in.”
The first available extension was to 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, Google says, with usage heavily skewed toward software developers. Notably, Gemini CLI is heavily used in the development and maintenance of its own codebase, closely overseen by product managers, as detailed in a recent TechCrunch interview.
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.”
