Google has officially rolled out a new feature for its Gemini command-line AI system (CLI), allowing external companies to integrate directly into the AI product. Dubbed Gemini CLI Extensions, the system launches with integrations from companies like Figma and Stripe, marking a significant move toward turning the AI tool into a broader development platform.
This announcement follows closely on the heels of OpenAI’s launch of apps in ChatGPT, which also integrated third-party services into its AI environment. However, Google is taking a distinctly different approach. While access to apps within ChatGPT is tightly curated, Gemini CLI Extensions can be published without any endorsement or participation from Google. The available extensions will be hosted in public repositories on GitHub and installed manually by developers.
“That open ecosystem is vital to us,” said Taylor Mullen, a senior staff engineer on the project, emphasizing Google’s commitment to a fair and accessible environment for all participants.
The first available extension was for Google’s own Nanobanana image generator, allowing users to generate images directly from the Gemini CLI terminal after installation.
The Gemini CLI, which launched in June, has already garnered over one million users, with its usage heavily skewed toward software developers. According to Google, the tool is heavily relied upon internally for developing and maintaining its own codebase.
Ryan J. Salva, Google’s senior director of product management for developer tools, explained that the purpose of the new feature is to evolve Gemini CLI into “an extensibility platform, a conduit to other tools and instructions that come from elsewhere in your tool chain.” Essentially, Google is aiming to position its AI terminal as the central hub connecting a developer’s entire workflow.
