Build your way: Use any AI agent of your choice in Android Studio
Google’s Android team has rolled out BYOA in the latest Android Studio Rabbit 2 canary, exposing a new Agent Client Protocol that streams full project graphs, build configurations, and platform metadata into the selected model. The integration promises token savings by letting the model focus on relevant files, while native hooks give agents control over Jetpack Compose previews, emulator sessions, and build diagnostics. Users can swap agents on the fly, grant granular permissions, and even spawn sub‑agents for tasks like code review, all within a single IDE window.
The move positions Android Studio alongside rivals such as Visual Studio Code and JetBrains’ IDEs, which have long supported third‑party extensions for GitHub Copilot, Tabnine, and others. By openly supporting any ACP‑compliant model, Google is betting that developers will favor flexibility over a single vendor lock‑in. The inclusion of Google’s own Antigravity agent—bundling the latest Gemini Flash 3.8 model and higher quota for AI Pro/Ultra subscribers—signals an attempt to keep the Google ecosystem attractive while still courting Anthropic and OpenAI users.
Looking ahead, BYOA could reshape Android development economics: token‑efficient prompts may lower per‑line AI costs, but the ability to run shell commands or edit files raises security concerns, especially for enterprise teams handling sensitive codebases. Monitoring how Google enforces permission granularity and audit trails will be crucial. Additionally, the success of BYOA will hinge on the maturity of third‑party agents’ Android‑specific knowledge bases; early adopters should watch for latency spikes or inaccurate diagnostics as models adapt to the new ACP data streams.
Key Takeaways
BYOA lets Android Studio users attach Claude, Codex, or Antigravity agents via a unified protocol, delivering project‑wide context for more efficient code generation.
The feature ships in the Rabbit 2 canary and includes native hooks for build tools, Compose previews, and emulator control.
Google’s Antigravity agent offers access to Gemini Flash 3.8 and higher usage quotas for AI Pro/Ultra plans, while still supporting external agents.
Enterprises should evaluate BYOA’s permission model and audit capabilities before granting agents file‑system or shell access.
About the Source
This analysis is based on reporting by Android Developers. Here is a short excerpt for context:
Posted by Matthew Warner, Product Manager, Android Developer Experience AI-powered developer tools have become an essential multiplier for engineering productivity, with teams adopting specialized AI coding agents, custom enterprise harnesses, and autonomous tools. It’s important for you to be able to build Android apps in the way that works best for you and your team, and agentic Android development is more open and flexible than ever before. 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. With our new Bring Your Own Agent (BYOA) feature, you can seamlessly integrate your preferred coding agent into Android Studio—featuring Anthropic’s Claude Agent, Open AI’s Codex, and Google’s Antigravity—and supercharge it with Android Studio’s AI-optimized infrastructure and tool support. Claude Agent in Android Studio Your agents, your AI plan BYOA pairs your favorite agent with IDE-native intelligence, making it faster, more accurate, and more cost-effective. BYOA is available in the latest Android Studio Canary with benefits including: Codebase awareness and token efficiency: Android Studio provides the full project graph, build setup, and platform details directly into your agent using Agent Client Protocol (ACP) . The agent can then filter to relevant files or details for efficient token usage, lower latency, and sharper answers. Seamless workflow continuity: Transition smoothly between multiple conversational agent prompts and Android Studio's purpose-built tools, keeping your flow state intact as you effortlessly jump between tasks. Agent flexibility: Connect any ACP-compliant agent directly into Android Studio, and sign in with your plan. If one agent runs out of quota or isn’t meeting your performance expectations, you can have another agent take over. Native tool injection: We wire up build diagnostics, UI tools like Jetpack Compose Previews, Android SDK tools, and Android emulator control so your agent has access and can test, diagnose, and execute directly in Android Studio. Powerful, capable, and reliable coding agents Agents can plan and execute complete technical workflows directly in your environment, unlocking powerful use cases: Execute in the environment: Read, write, and edit files, run shell commands, run tests, and search the web. Delegate to subagents: Break down complex projects by spawning specialized agents for subtasks like code review or testing. Stay in control: Granular permissions let the agent act on its own for routine work, and pause for your approval on riskier actions. Persist context and configuration: Maintain long-running sessions and automatically load project skills, slash commands, and memory. Agents running in Android Studio also benefit from Android skills and the Android Knowledge Base, ensuring they have access to the latest Android best practices. And if you want to learn more about how agents impact model performance, read more about our latest updates to Android Bench. Using Gemini with Google Antigravity Many developers have been using Gemini directly in Android Studio through the built-in agent, and we will continue to offer this experience in Android Studio. However, for the best experience with Gemini, we recommend selecting the Google Antigravity agent for access to the latest Gemini models such as Gemini Flash 3.8, along with increased AI usage quota. You can also login to the Google Antigravity agent with your Google AI Pro or Ultra plan to take advantage of your benefits in Android Studio, or pay per token rates with a Gemini API key. Selecting the Google Antigravity agent Selecting the Google Antigravity agent If your organization is using Gemini Enterprise, you can continue to use the built-in agent or the Antigravity agent. In either case, your organization continues to benefit from the added security and privacy of Google Cloud. Log in to the Antigravity Agent using a Google account, Gemini Enterprise license, Enterprise Agent platform or Gemini API key Get started BYOA support is rolling out in preview starting with the canary release of Android Studio Rabbit 2 featuring commonly used agents like Google Antigravity, Claude Agent, and Codex. Both enterprise and consumer AI plans are supported - subject to the agent provider. To connect an agent, follow these steps: Update Android Studio: Ensure you are running the latest from the canary release channel. Connect your agent(s): In the agent window, select one of the agents (Claude Agent, Codex, or Antigravity) and sign-in or provide an API key. Additional agents can be found in the registry Settings > Tools > AI > Agents Explore the docs: Check out our preview release note here. Your feedback is essential as we continue to refine the AI experience in Android Studio. If you find a bug or issue, please file an issue. We can’t wait to see what you build!Read the original at Android Developers
