Google has announced it is discontinuing Gemini CLI, merging its functionality into the newly launched Antigravity CLI as part of their agent-first Antigravity platform. This change aims to deliver a unified developer experience, shifting all efforts and support to Antigravity CLI and its server-side harness. While feature parity is not complete from the outset, Antigravity CLI retains the most critical Gemini CLI features, such as agent skills, hooks, subagents, and extension support, reintroduced as Antigravity plugins. Antigravity CLI is built in Go and offers a faster, more responsive interface. It can orchestrate multiple agents in the background, enabling developers to handle complex code refactors or multi-topic research without blocking their terminal. The tool shares its agent harness with Antigravity 2.0, the new desktop app, allowing core agent improvements to propagate automatically across supported platforms. Developers can continue workflows like code scaffolding, cloud p...
Related
OpenCV 5 brings new deep neural network engine, stronger ONNX support, and faster core
OpenCV 5 has been released as a major new version of the widely used open source computer vision library. The update delivers several foundational changes including a new deep neur...
Google's Gemini 3.5 Live Translate enables real-time multilingual speech in 70+ languages
Google has released Gemini 3.5 Live Translate, its latest audio model aimed at supporting live speech-to-speech translation. The model automatically detects more than 70 languages ...
Anthropic launches Claude Fable 5, a “safe” Mythos-class model with safeguards attached
Anthropic has released Claude Fable 5, a Mythos-class artificial intelligence model, now available for general use worldwide. Users accessing Fable 5 benefit from its expanded capa...