Android Dev Summit 2026 Introduces AI Agents and XR Emulators to Reshape App Development

Google Enables XR App Development Without Expensive Hardware

At the Android Dev Summit 2026, Google announced a significant shift in how developers approach XR app development by releasing stable Android XR emulators in Android Studio1

1

. This update eliminates the barrier of purchasing expensive smart glasses just to test applications, letting developers simulate different types of smart glasses directly from their computers. The core Jetpack XR SDK libraries have reached production-ready status, providing developers with stable tools to build extended reality applications1

1

.

Google also introduced Geospatial APIs, which enable developers to anchor digital objects to real-world locations—such as placing navigation markers at street corners or displaying landmark information through AR glasses1

1

. For developers working with Unity, Godot, and Unreal, Google released a stable Android XR Engine Hub to help analyze performance. The XREAL AURA, announced alongside these updates, marks the first wired XR glasses powered by Android XR1

1

.

AI Coding Agents Get Over 30 Android Skills for Enhanced Developer Productivity

Google has transformed Android Studio and Android CLI into platforms that support AI-driven development through extensive agent integration. Android Studio Rabbit 2, now stable, allows developers to choose coding agents directly within the IDE, with supported options including Claude Agent, Codex, Antigravity and more than 40 agents compatible with the Agent Client Protocol (ACP)2

2

.

The Android CLI has gained capabilities that let AI coding agents do more than generate code. Agents can now remotely test apps on real Android devices through Firebase-powered Android device streaming1

1

2

2

. They can generate Jetpack Compose previews to check how an app looks without launching an emulator or installing it. Performance profiling through Perfetto system traces helps developers investigate cold startup latency, UI jank and background wakeups to analyze app performance and memory usage2

2

.

Google introduced over 30 Android skills covering more than 20 areas to help agents handle complex tasks, including permission security, Glance widget layouts and Compose performance optimization2

2

. The Android plugin for Google Antigravity has been updated with the latest Android CLI capabilities, and Google launched official Android plugins for Claude Code and Codex by OpenAI2

2

.

Agentic APIs Connect Apps to Gemini Across Android Ecosystem

Google introduced agentic APIs that let developers expose app functionality to AI agents and build interactive experiences through the Android intelligence system. The Connected Apps Platform allows developers to prototype a Connected App to share their app's services with Android users when Gemini acts as the system AI agent2

2

. Developers can build integrations using Android MCP or remote MCP, prototype through Gemini developer mode and register through the Google Connected Console preview program when preparing for production.

AppFunctions, now in beta, serves as Android's unified tool-calling layer, letting developers expose app functionality to on-device or system agents through Android MCP2

2

. The Agent-to-UI (A2UI) feature for Jetpack Compose, available in alpha, lets agents return interactive interfaces built from an app's own components instead of presenting responses as text2

2

.

The ML Kit Agentic API, available in alpha, extends the ML Kit Prompt API with Gemini Nano 4 capabilities for on-device agents. It automatically executes functions, saves conversation history, manages the orchestration loop and includes automatic guardrails2

2

.

Enhanced App Quality Analysis and Adaptive Development Tools

Google upgraded app quality checks within Android CLI, using the same logic as Google Play to identify potential issues before upload. The Analyze feature checks app bundles and libraries, including AAs and Js, for quality signals related to obfuscation, optimization and shrinking2

2

.

For adaptive development across different screen sizes and device configurations, Google announced updates to Jetpack Compose. AppState, now in alpha, brings Compose's reactive model to the state layer with Compose-first architecture building blocks that help developers and AI agents preserve state across device configurations2

2

. Navigation 3 version 1.2, now stable, adds deep-link support and richer predictive back handling2

2

.

The upcoming Compose 1.13 stable release will add built-in adaptive layout support, with Grid and Flexbox moving to stable, along with Progressive Blur and Formatted Text2

2

. Google updated its Compose adaptive skill to help agents adapt existing apps for Googlebook, phones, foldables, tablets, parked cars and XR devices, with desktop-specific improvements and foldable posture optimizations2

2

. Matthew McCullough, Vice President of Product Management for Android Developer, said the updates aim to reduce everyday development friction and give developers more flexibility when building Android apps2

2

.