Google launches extensions system for its command-line coding tool

On Wednesday, Google introduced an exciting new feature for its command-line AI tool, Gemini CLI. This innovative addition, known as Gemini CLI Extensions, allows external companies to seamlessly integrate their services into the AI platform. Among the first to join this initiative are notable names like Figma and Stripe. This announcement closely follows OpenAI's recent rollout of applications within ChatGPT, which also aim to incorporate third-party functionalities. However, unlike the curated approach taken by ChatGPT, Gemini CLI Extensions can be published without requiring Google's endorsement or involvement. Developers will find these extensions available in public repositories on GitHub, which they can install manually. Taylor Mullen, a senior staff engineer on the project, emphasized the importance of this open ecosystem, stating, "Everything we’re doing is grounded in a fair ecosystem that anyone can participate in." The first extension to be launched is for Google’s own Nanobanana image generator, which was made available on GitHub last week. This extension enables users to create images directly from the Gemini CLI terminal. Since its launch in June, Gemini CLI has reportedly amassed over one million users, with a significant portion being software developers. The tool is notably utilized in the development and upkeep of Google’s own codebase, a process closely monitored by product managers, as highlighted in a recent interview with TechCrunch. In discussing the new feature, Ryan J. Salva, Google’s senior director of product management for developer tools, explained that the goal is to transform Gemini CLI into "an extensibility platform, a conduit to other tools and instructions that come from elsewhere in your tool chain."