Google opens Android Studio to outside agents and Gemini APIs
Original title: Google opens Android development to third-party AI agents and unveils new Gemini APIs
Rabbit 2's Bring Your Own Agent feature runs more than 40 agents, including Claude, Codex, and Antigravity, through ACP.
At the Android Dev Summit, Google launched Android Studio Rabbit 2 so developers can run Anthropic, OpenAI, and Google coding agents in the IDE via the Agent Client Protocol. New ML Kit and AppFunctions APIs use Gemini Nano 4 and MCP so apps can expose tools to local or system agents. Google also marked Jetpack XR tooling stable and, with XREAL, unveiled wired Android XR glasses.
Unconfirmed: Speed and token-savings figures come from Google's own internal and A/B tests.
- Developers can install Claude Agent, Codex, and Google Antigravity from a marketplace.
- An alpha Agentic API in ML Kit is powered by Gemini Nano 4.
- Google says over 50 partner integrations are already live in the Gemini app.
- XREAL AURA glasses weigh under 95 grams and show up to five app windows.
- Google's tests claim UI tasks finished 77 percent faster with new CLI previews.
From the original article
5 min read at the-decoder.com
Google is opening up Android Studio to third-party AI agents. Through a new "Bring Your Own Agent" feature, the IDE now supports more than 40 coding agents, including Anthropic's Claude Agent and OpenAI's Codex. Google says new terminal tools also help agents finish UI tasks 77 percent faster while using up to three times fewer tokens.
By Maximilian Schreiner · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.