As agentic development accelerates, Android engineering is reaching an exciting new frontier: moving from assistive code completion to agents executing end-to-end under your direction. You have total choice and flexibility in the models and agents you use.
Gemini 4 Argon excels at deep work in complex, real-world tasks across domains including coding, finance, legal, cybersecurity, and science.
Starting today, Android developers can access Gemini 4 Argon across their development surfaces, including Google Antigravity (standalone and in Android Studio Canary) for Google AI Ultra subscribers, and in Android Studio and Google AI Studio via the paid tier of the Gemini API.
Argon has significant improvements in long-horizon autonomous execution and the ability to plan and run multi-step, complex software tasks over time.
Argon demonstrates exceptional design craft, generating production-ready Jetpack Compose code out of the box:
Antigravity operates across multiple surfaces, from the desktop app and IDE extensions to the command line. No matter which surface you prefer, the official Android CLI plugin is the de-facto engine that connects your agent to local Android tools, enabling it to run programmatic commands for common tasks and execute custom developer skills.
Starting today, you can access and configure this agentic workspace in two primary ways:
1. Setting up visually (Antigravity Desktop & Android Studio Canary)
3. For any terminal agent (via Android CLI), run:
Starting today, Argon is rolling out globally to developers in supported regions. You can access and begin building with the model in your local environment across three primary development surfaces:
1. Google Antigravity: Google AI Ultra subscribers can build with Gemini 4 Argon in the standalone Antigravity desktop app (available for macOS, Windows, and Linux) or directly via the terminal CLI
3. Google AI Studio: Google AI Ultra subscribers or developers on the paid tier of the Gemini API can build with Gemini 4 Argon via Playground and Build in Google AI Studio
4. Firebase AI Logic: Starting today, developers globally on the paid tier of the Gemini API can use Gemini 4 Argon client-side to build intelligent features in their mobile and web apps via Firebase AI Logic.
To begin building with Argon in your local environment:
We are eager to see the high-craft Android experiences you build at the frontier. Share your projects and feedback with us on X (@AndroidDev) and LinkedIn!
As Android developers, you have many choices when it comes to the agents, LLMs, tools, and command-line interfaces (CLI) you use for app development. Our goal is to help you build beautiful, high-quality Android apps, no matter how you choose to build.
Last year, Android Studio opened up to any AI model. Today, we’re taking the next step by introducing support for your choice of coding agents.
Today we’re releasing the first set of long-horizon tasks (LHT), which are tasks of great complexity that take an engineer multiple days or even a week to complete. We are also introducing agentic evaluation, starting with agents from corresponding model providers.
Get the latest Android development insights delivered to your inbox weekly.
