Source: Android Developers Blog

Today we're excited to launch Developer Preview 4 of the Android XR SDK, continuing our focus on unifying cross-device development for headsets, wired XR glasses, and intelligent eyewear. To keep our platform intuitive, we are adopting more descriptive naming for our form factors, where AI glasses are now audio glasses and display AI glasses are now display glasses, with these changes appearing in our documentation starting today.

This release is packed with updates that help you build incredible experiences for XR devices, enable deeper immersive experiences on XR headsets, and streamline the path for creating augmented experiences on audio and display glasses. Also, our core libraries—including XR Runtime, Jetpack SceneCore, and ARCore for Jetpack XR— will be officially moving to Beta soon!

To give you early access to hardware and resources for building immersive and augmented experiences on upcoming devices—like display and audio glasses and XREAL’s Project Aura — we’re announcing the Android XR Developer Catalyst Program. Learn more and start your application today.

Building Augmented Experiences for Audio and Display Glasses

Starting out with our libraries for augmented experiences, Developer Preview 4 introduces new APIs that help you create and test your apps.

The Jetpack Projected library helps bridge app experiences from the phone to the user's field of view. We've added the Device Availability API, which consolidates wear state and connectivity signals into standard Android Lifecycle.State values. This lets you adjust your applications behavior based on whether the device is worn.

val xrDevice = XrDevice.getCurrentDevice(projectedContext)

// Observe the device lifecycle flow
xrDevice.getLifecycle().currentStateFlow
    .collect { state ->
        when (state) {
            Lifecycle.State.STARTED -> { /* Device is available (worn) */ }
            Lifecycle.State.CREATED -> { /* Device is unavailable (not worn) */ }
            Lifecycle.State.DESTROYED -> { /* Device is DISCONNECTED */ }
        }
    }
  

To simplify testing, the new ProjectedTestRule API in the projected-testing artifact automates the setup of projected test environments. This helps you write clean, reliable unit tests without the boilerplate code.

// from the 'androidx.xr.projected:projected-testing:1.0.0-alpha07' artifact
@get:Rule
val projectedTestRule = ProjectedTestRule()

@Test
fun testProjectedContextInitialization() {
    // by default, ProjectedTestRule automatically creates and connects
    // a projected device before each test
    val projectedContext = ProjectedContext.createProjectedDeviceContext(context)

    // assert the projected context is successfully initialized
    assertThat(projectedContext).isNotNull()
}
  

Our UI library for display glasses, Jetpack Compose Glimmer, now includes Google Sans Flex for improved legibility on optical see-through displays. We’ve also added several interactive components:

• Stacks: Designed for touchpad-optimized groups, showing one item at a time.
• Title Chips: Provides categorization and context for content cards.

Building Immersive Experiences for XR Headsets and Wired XR Glasses

If you're looking to build fully immersive experiences for XR Headsets and wired XR Glasses, we have several big updates.

XR Runtime, Jetpack SceneCore, and the ARCore for Jetpack XR perception features (Depth Maps, Eye/Hand Tracking, Hit Testing, and Spatial Anchors) will soon move to Beta, so we’ve streamlined the Jetpack XR APIs. We've removed legacy Guava and RxJava3 packages in favor of a modern, Kotlin-first architecture.

We're expanding 3D model capabilities by adding the ability to fine tune 3D models and access specific nodes with a 3D model. Using GltfModelNode, you can modify properties like pose, materials, and textures, and even run animations for specific nodes.

// Create a new PBR material
pbrMaterial = KhronosPbrMaterial.create(
    session = xrSession,
    alphaMode = AlphaMode.OPAQUE
)

// Load a texture.
val texture = Texture.create(
    session = xrSession,
    path = Path("textures/texture_name.png")
)

// Apply the texture and configure occlusion
pbrMaterial.setOcclusionTexture(
    texture = texture,
    strength = 0.5f
)

// Access the hierarchy of nodes
val entityNodes = entity.nodes

// Find the specific node
val myEntityNode = entityNodes.find { it.name == "node_name" }

// Apply the PBR material override
myEntityNode?.setMaterialOverride(
   material = newMaterial
)
  

// Create the mesh
val roadMesh =
    CustomMesh.BuilderFromMeshData(session, roadVertexLayout)
        .addVertexData(ByteBufferRegion(roadDataBuffer, 0, vertexDataSize))
        .setIndexData(ByteBufferRegion(roadDataBuffer, vertexDataSize, indexDataSize))
        .setTopology(MeshSubsetTopology.TRIANGLES)
        .build()

// Define the material
val roadMaterial = KhronosPbrMaterial.create(session, AlphaMode.OPAQUE)

// Instantiate the entity using the custom mesh and material
val roadEntity =
    MeshEntity.create(
        session,
        roadMesh,
        listOf(roadMaterial),
        pose = roadPose,)

We now have native glTF support directly in Compose for XR with SpatialGltfModel. Use this along with SpatialGltfModelState to access nodes and animations in the glTF model, or use them to add textures and materials to your 3D models.

   val myGltfModelState = rememberSpatialGltfModelState(
        source = SpatialGltfModelSource.fromPath(
            Paths.get("models/my_animated_model.glb")
        )
    )

    val myGltfAnimation =
        myGltfModelState.animations.find { it.name == "animation_name" }

    DisposableEffect(myGltfAnimation) {
        myGltfAnimation?.loop()

        onDispose {
            myGltfAnimation?.stop()
        }
    }

    SpatialGltfModel(state = myGltfModelState, modifier = modifier)
  

We’re also providing an early preview of the Geospatial API for wired XR Glasses in ARCore for Jetpack XR. This update enables high-precision anchoring of digital content tied to real-world locations in over 87 countries.

By combining ARCore’s Visual Positioning System (VPS) with the reasoning and audio capabilities of the Gemini Live API, you can create contextually aware experiences that understand both the location and position of your user. Imagine building an immersive, AI-guided walking tour that provides real-time audio descriptions of nearby places, seamlessly blending digital information with the physical environment.

Start Building the Future Today

It's an amazing time to develop for Android XR. With the Jetpack XR SDK moving to Beta soon and a robust set of new tools at your fingertips, explore each of the following areas to get your app's experiences ready for XR!

Head to the official Android Developer site for full technical guides, API reference, and instructions on setting up the new emulator. Get inspired with our samples and experiments. See how we've used these APIs to build immersive spatial layouts, load 3D models, explore spatial audio, and more!

• Visit the Android XR webpage
• Explore XR examples
• Explore XR experiments

We've added official support for Unreal Engine and Godot, and we've launched two new tools to accelerate development for Android XR with Unity and the Android XR Interaction Framework. And, based on your feedback, we are introducing the Android XR Engine Hub to allow you to run your experiences directly from your preferred engine,

• Read the blog post about what's new for game engines

Don’t miss your chance to build for the latest Android XR hardware. Apply today for the opportunity to gain access to pre-release hardware, including our audio and display glasses prototype and XREAL’s Project Aura.

• Learn more and apply today.

We look forward to seeing the amazing XR experiences you build as we move toward the launch of more Android XR devices later this year!

Explore this announcement and all Google I/O 2026 updates on io.google.

Source: Android Developers Blog

Source: Android Developers Blog

This year at Google I/O we are going beyond iterative changes, towards a fundamental shift in how apps are built. Our newest tools are built for the agentic era with features that boost productivity for you as an Android developer AND supercharge the AI agents you deploy in your codebase. So, whether you are building exclusively with AI or you prefer being the architect of every line of code, our tools will keep you ahead of the curve.

As we move from "AI-assisted" to "Agentic" development, we’re making it easier than ever to turn a spark of an idea into a high-quality production app with significantly less developer effort.

So what’s new with Android developer tools? We will cover 3 main areas in this blog:

• Let your agent handle it: Whatever development task you are working on, the Android Studio agent can help: from planning the app architecture and design, to writing code, to unit testing and bug fixing.

• Any AI provider, anywhere you build: In Android Studio, you can use any model and we even help guide you to the best performing ones. Choose any of the top remote models from Google, Anthropic, OpenAI, or if you need to run locally - Gemma 4 is our most capable and efficient local model! And with Android CLI, you can build Android apps faster and easier using the agents and developer environments of your choice.

• As always, performance and quality remain top priorities: We continue to invest in the Android developer tools you love: from the Emulator, to Profilers, performance analyzers, and more!

1: Let your agent handle it

Agent skills

Android Studio now supports Agent Skills, modular instruction sets that ground LLMs in specialized workflows and domain-specific knowledge. By adding skills to your project, you can teach the agent to follow specific best practices, architecture patterns, or library workflows. This enables more accurate, context-aware code generation and automated skill activation for an appropriate task, ensuring the agent acts as an expert. We’ve bundled many of the top Android and Firebase agent skills in the latest Android Studio Canary build, so you can skip straight to building!

Skills in Agent Mode

You can create your own skill, or use Android CLI to install our official skills - a repository that covers some of the most common workflows that some Android developers and LLMs may struggle with. They help models better understand and execute specific patterns that follow our best practices and guidance on Android development, such as XML to Compose migration, Edge-to-edge, Navigation 3, and more. You can even build for Android XR, starting with a beautiful Display Glasses app with Jetpack Compose Glimmer. Official Android skills are automatically bundled with the latest Android Studio so the Agent is ready to build!

Build full-stack apps with Firebase in Agent Mode

Firebase services like Auth and Firestore databases can now be enabled directly within Agent Mode in Android Studio using the Agent Skills for Firebase. Your agent will be able to complete Firebase integration and configure backend services. This integration empowers you to build robust, full-stack Android applications without ever leaving your IDE!

Parallel conversations

You can now run multiple conversations with Agent Mode in parallel. In one conversation, run tests and while you are waiting, you can kick off planning mode for a new feature in your app while using a third conversation thread to write documentation for your app. These improvements will save you time and improve your productivity. 

A more capable New Project Agent

Android Studio's New Project Agent has evolved into a powerful full-stack development tool, utilizing a multi-step execution plan and an autonomous "generation loop" that self-corrects build errors and configures dependencies across multiple files. This advanced capability is significantly amplified by its new integration with Firebase Agent Skills, allowing developers to seamlessly build, debug, and deploy complete full-stack applications directly from a single prompt to final production.

Additionally, it now offers support for large screens. You can scaffold your project with layouts, navigation, and components optimized for tablets, foldables, and laptop devices from the get-go. It has additional logic to test your app on large-screen emulators if you have one enabled. Simply configure the required device in the Android Emulator and the Agent can test it out!

2: Any AI provider, anywhere you build

Build Android apps in Google AI Studio

Google AI Studio now features full Android app development capabilities. Users can generate new applications, preview them instantly via an embedded Android Emulator, and deploy them directly to physical devices using ADB over USB. Additionally, developers can publish straight to Google Play; AI Studio handles the app record creation, bundles the package, and uploads it to an internal testing track. For advanced development and production readiness, projects can be exported as a ZIP file and opened seamlessly in Android Studio. To get started, visit Google AI Studio today and start building!

Google AI Studio build mode with Android framework

Android CLI helps you build faster, more efficiently with any agent

Android CLI enables you to build apps using any agent, LLM, and tool of your choice. Android CLI is designed to help AI agents build faster, and use less tokens when compared to only using generic LLM tools. By grounding agents with Android Knowledge Base and Android skills, you can now have your agent of choice follow the latest best practices across any coding environment.

Google AI plan

Android Bench highlights the top models

Latest results as of May 18th 2026, check here for updates

3: As always, performance and quality remain top priorities:

Test multi-device interactions with the Android Emulator

The Android Emulator now features a new networking stack that enables zero-configuration, peer-to-peer connectivity between multiple virtual devices on the same host machine. This update eliminates the need for manual port forwarding, allowing developers to easily test multi-device scenarios like local multiplayer gaming, file sharing, and companion app pairing. By creating a shared virtual network backplane, the Android Emulator provides a more stable and consistent environment for building complex, interconnected app experiences across different form factors.

Multi -device testing with the Android Emulator

Android Debug Bridge Wi-Fi 2.0

ADB Wi-Fi 2.0 offers significantly more reliable wireless debugging. With the latest ADB command line tool from Android Platform Tools v37 and an Android 17 device, you can now change networks, shut down your machine, and go about your typical day and your devices will stay connected. Additionally, devices with wireless debugging enabled will automatically show in Android Studio’s Device Manager, streaming the pairing process and making it easier than ever to connect Android phones, watches, and more.

Pair devices with Wi-Fi

Android Studio now lets you publish to Google Play for testing

Android Studio now gives you the ability to upload new releases of your app directly to Google Play Console test tracks. You can do this by selecting a new option to continue to “Publish for Testing” at the end of the Generate Signed App Bundle flow. This integration supports uploading an initial release of a brand-new app to Play Console’s internal test track. You can also use this feature to upload releases to existing apps to test tracks. You need to be registered on Google Play Console to take advantage of this functionality. Read the ‘What’s new in Google Play’ blog to learn about all the updates from Play at I/O.

Upload App Bundle to Google Play

Android developer verification support

You can now see your app's registration status right in Android Studio when you generate a signed App Bundle or APK. Seeing this information in Android Studio enables you to address registration issues early and ensure your apps are ready before the verification requirement goes into effect for certified Android devices starting in September 2026.

App registration status with Android developer verification

Memory leak detection with LeakCanary

Memory leaks in Android occur when your code holds onto an object's reference long after its life cycle has ended. This prevents the Garbage Collector (GC) from reclaiming that memory, eventually leading to sluggish performance or OutOfMemoryError (OOM).

The Android Studio LeakCanary profiler task significantly enhances developer productivity by enabling the analysis and inspection of memory leak traces directly on the desktop development environment rather than on the mobile device. Furthermore, Android Studio streamlines troubleshooting by providing tools like “Go to declaration” to map the leak analysis directly to the codebase, allowing developers to quickly locate and resolve memory leaks.

Starting from the Android Studio Quail 1 release, you can now also request Gemini to review the memory leak for you using the “Fix with Agent” button.

Review memory leaks identified via LeakCanary through the “Fix with Agent” button

Android Performance Analyzer (APA)

Android Performance Analyzer (APA) is the next generation of performance profiler for Android and provides a cohesive analysis of CPU, GPU, memory, and power usage for your apps and games running on Android 12+ devices. APA is engineered for reliability and performance with trace rendering speeds which are up to 26x faster from previous tooling.

Android Performance Analyzer (APA) running in Android Studio showing two traces side by side

APA integrates natively with AI agents and offers two new skills: Perfetto SQL skill and the Perfetto Analysis skill, which helps with questions like "Why is my app startup slow?"

Analysis of traces using Perfetto Analysis skill

R8 Configuration Analyzer

R8 is one of the best ways to improve your app’s performance and reduce memory footprint. The performance benefits you can get from R8 are directly correlated to how much of your codebase R8 is able to optimize. We’ve introduced a new tool to help you to unlock the maximum optimization from R8 – the R8 Configuration Analyzer. It provides insights into R8 configuration quality and how your keep rules impact your app. We have also introduced three scores that show how much of your codebase is available for optimization, obfuscation, and shrinking.

Suggested fixes for crashes with Agent integration in AQI

The App Quality Insights tool window is now integrated with the AI agent to analyze crash data along with your source code to provide detailed explanations and suggest potential fixes. After selecting a crash in the App Quality Insights tool window, navigate to the Insights tab and click “See more” to see a detailed explanation of the crash. Click “Fix with AI” to have the agent suggest code changes that you can review and accept.

App Quality Insights and Fix with AI

Get started

Android Studio is closing the gap between ideation and implementation. With powerful tools built for agentic development, it’s never been easier to build and ship high-quality Android apps.

Download the latest Android Studio Quail preview build and try these new features. As always, your feedback is crucial to us. Check known issues, report bugs, and be part of our vibrant community on LinkedIn, YouTube, or X. Happy coding!

Explore this announcement and all Google I/O 2026 updates on io.google.

Source: Android Developers Blog

The AppFunctions API allows developers to integrate their apps with agents and assistants, like Google Gemini, enabling users to complete tasks using voice, often replacing the need for step-by-step, manual navigation with your UI.  

For example, to start a run with the Samsung Health app, users are able to tell Gemini: “Start tracking my run.”

We’re currently running an Early Access Program for any developers who are interested. Sign up in our form to express your interest.

Also coming soon, without any development effort at all, users will be able to invoke and track automated app tasks, for selected phone apps, directly from their watch, like placing an order with DoorDash!

Keep an eye out for these flexible options on how to prepare and connect your app to the Android intelligence system on our developer blog.

Wear Workout Tracker

Source: Android Developers Blog

Build High Quality Android Apps Using Agents

1: Android CLI: helping you build with any agent, LLM, and tool

2: Build production-ready apps with ease in Google AI Studio

Use the embedded Android Emulator to create Android apps in Google AI Studio

3: Accelerating AI coding assistance with Android Bench

4: Convert iOS apps to Android with the Migration Assistant in Android Studio

Building AI Into Your Apps

5: Building Intelligent Apps with generative AI

6: Experiment with AppFunctions today

The Future is Adaptive

7: Android is now Compose First; Views are now in maintenance mode.

8: Building seamless Android experiences across devices with Jetpack Compose

The Android ecosystem is now Adaptive by Default, moving fluidly across phones, foldables, tablets, cars, XR, and expanding usages with Googlebook and connected displays. With over 580 million large-screen devices, and users on multiple devices spending up to 14x more on apps, the investment in adaptive design presents a massive opportunity. Jetpack Compose is the definitive engine for this transition, offering core tools like our latest Jetpack Navigation 3 release, new experimental Grid and FlexBox layouts, enhanced non-touch input support, and CameraX for correct camera previews across any window size. Furthermore, new skills in Android Studio make updating your existing app to adopt these adaptive patterns easier than ever. Notability’s Android debut sets a new standard for premium productivity apps. Built with Jetpack Compose, Navigation 3, and Kotlin Multiplatform, it delivers an intuitive, adaptive experience across devices.

9: Create seamless experiences for Googlebook

10: Unified widget development experience with Jetpack Glance

12: Accelerate your development with Android XR Developer Preview 4

13: Android is your new home for professional-grade media experiences

14: Increase app discovery and engagement on Google TV

15: Performance: the foundation of a great app experience

And The Latest on Driving Business Growth 

16: What’s new in Google Play

17: And of course, Android 17

Check out all of the Android & Play Content at Google I/O 

This was just a preview of some of the updates for Android developers at Google I/O. Tune into What’s New in Android for the latest news and announcements and follow Google I/O for much more over the following week!

Source: Android Developers Blog

The power of native Android

A seamless, end-to-end workflow

Start building today

What’s Next?

Turn your Google Pixel Watch into an aviation assistant

Prompt: Build a small airplane "6-pack" instrument app for Google Pixel Watch. The 6 instruments should include attitude indicator, airspeed indicator, altimeter, turn coordinator, vertical speed indicator, and heading indicator. Use the Google Pixel Watch's sensors to power the instruments and display them clearly. Display one instrument at a time on the display. Swiping to the left or right should cycle through the instruments.

Interactive Harmonium app on Google Pixel Fold
Prompt: Build a Harmonium app for Pixel Fold devices, which plays like the instrument based on the hinge angle and touch gestures. The app should simulate the bellows and reeds accurately.

An Android app for guitarists to become better musicians by jamming to backing tracks

Prompt: Build an Android guitar practice companion app that features a two-tab navigation system: 'Fretboard' and 'Library'. The 'Fretboard' primary screen must contain an interactive guitar neck UI that visually maps out user-selected root notes, musical scales, and chords. Above the fretboard, implement a WebView-based YouTube player configured to play embedded videos inline. Additionally, include an AI generation feature that uses Retrofit to call Gemini Lyria 3 to create custom, 30-second backing tracks based on the user's currently selected key and scale. The generated audio files and their metadata must be saved locally using a database and displayed as a list in the 'Library' tab, where users can delete or play them. Finally, implement a persistent, globally visible mini audio player at the bottom of the screen, complete with play/pause toggles, a progress slider for seeking, and timestamp text, allowing the user to seamlessly practice on the fretboard tab while listening to their tracks.

Source: Android Developers Blog

With over 300 million monthly active devices across Google TV and Android TV, it’s clear that the living room is a massive, distinct platform for apps to accelerate growth. Today, we’re excited to share Google TV features and developer tools designed to increase the discoverability of your content and prepare your app for future TV experiences.

Drive discovery and engagement with Gemini

Last year, we brought our AI voice assistant, Gemini, to our platform, so that people can easily find what to watch, learn something new on the big screen, and get everyday tasks done with just their voice.

Since launch, we’ve made improvements to how Gemini provides tailored responses to questions. Gemini shares a mix of visuals, videos, and text to help users find what they need, when they need it. For our streaming partners, Gemini is a helpful discovery engine—pulling from your app's metadata to surface your relevant content to viewers.

Declare support for pointing modality

The TV experience that we once knew is changing. Gemini is changing the way we discover and stream content with voice, but how we use the remote is evolving, too.

Pointer remotes bring motion-controlled input to the big screen, unlocking faster user navigation across the Google TV Home page and within content-heavy apps. To ensure your app is ready for this shift and provides a great experience for all users, now is the time to start thinking about pointing input. Here’s how to get started:

1. Adapt your TV app UI Library

You’ll need support for hover states, scrollable containers, and cursor clicks to enable pointer remote interactions for your app on Google TV. While implementation varies by UI stack, Jetpack Compose streamlines this transition, as most core components handle these multi-modal interactions natively out of the box.

1. Hover state: Every focusable element on your screen (buttons, movie posters, setting toggles) needs a clear visual feedback mechanism for a hover state. This is often subtler than a focus state but critical for feedback.
2. Scrollable containers: Pointer remotes will also have a small circular touchpad for scrolling. Users can use this touchpad to scroll up or down, or left or right in your app. Your app will need to respond to touch events to scroll.
3. Cursor clicks: Many TV apps today expect a simple D-pad OKAY button “click.” With a pointer remote, a user may “click” on an element that’s not the D-pad focus state, but is instead from a hovered state (similar to a mouse click).

2. Test pointing interactions with a mouse today

To see how your app handles hover, scroll, and clicks, simply connect a bluetooth mouse or wired mouse to your Google TV. Keep in mind that a mouse has more precise control, since users are closer to the screen and typically rest the mouse in a stable position. Pointer remotes can often be less precise, since users are sometimes 10 feet away from the screen, making rough gestures with the remote from their couch. As a TV designer or developer, you can mitigate this lack of input precision by having larger hover targets for elements.

3. Declare TV app support for pointer remotes on Google Play

Finally, tell Google Play that your TV app is designed to work with a pointer. This ensures that users with pointer remotes will be able to easily find, install, and interact with your app.

Within your AndroidManifest.xml, declare the meta-data tag, android.software.leanback.supports_touch. This tag informs the platform that your TV app “spatially supports touch,” since pointer remotes simulate touch events from a distance.

AndroidManifest.xml

<manifest ...>
    <!-- Signal whether the app is adaptive or built just for TV -->
    <uses-feature android:name="android.software.leanback" android:required="true|false" />

    <!-- Ensure the app can be installed on conventional TVs -->
    <uses-feature android:name="android.hardware.touchscreen" android:required="false" />

    <!-- Signal whether the app supports pointer remotes -->
    <meta-data android:name="android.software.leanback.supports_touch" android:value="true|false"/>

    <application ...>
        ...
    </application>
</manifest>

Tips:

• The android.software.leanback feature declaration indicates that your app supports D-pad navigation and is intended for distribution only on TV devices via Google Play.
• The new software attribute of android.software.leanback.supports_touch declares that in addition to D-pad, you have ensured that your TV app works well for pointer/cursor experiences via mouse (of today) and pointer remotes (of future).
• If you haven't already, now is the time to adopt Jetpack Compose. Hover, scroll, and clicks are common input modalities that are supported on various form factors, and building your app with an adaptive UI framework enables code reusability and reduced maintenance.

Onboard the Engage SDK

The Engage SDK, formerly known as the Video Discovery API, optimizes Resumption, Entitlements, and Recommendations across all Google TV form factors to boost app discovery and engagement.

• Resumption: Partners can easily display a user's paused video within the 'Continue Watching' row from the Home page.
• Entitlements: The Engage SDK streamlines entitlement management, which matches app content to user eligibility. Users appreciate this because they can enjoy personalized recommendations without needing to manually update all their subscription details. This allows partners to connect with users across multiple discovery points on Google TV.
• Recommendations: The Engage SDK even highlights personalized recommendations based on content that users watched inside apps.

It’s a great time to start onboarding the Engage SDK now, since the legacy Watch Next API, which has been powering your continue watching 1.0 experience, will lose support in the 2nd half of 2027. To get started, head to goo.gle/engage-tv to learn more.

We're excited to see how our latest Gemini experience and developer tools will optimize your discovery and drive user engagement on our platform.

Source: Android Developers Blog

At Google I/O ‘26, we shared the latest leaps forward in agentic development, and showcased some of the newest capabilities of Android CLI—now stable at version 1.0 and ready for all Android developers to use. From new skills to enabling agent access to powerful Android Studio capabilities, we’re giving your agents the right tools to build alongside you.

Android development unlocked for Antigravity

Google Antigravity now includes an optional bundle of Android resources—including the Android CLI and skills—that you can install. You can either install the bundle during onboarding after installation, or later from the Settings > Customizations > Build With Google Plugins menu.

This provides Antigravity with all the powerful tools and knowledge of Android CLI, enabling it to perform the core tasks necessary for Android app development more easily and efficiently—from creating projects to deploying your app on a new Android virtual device.

Unlocking Android Studio capabilities for any agent

Android CLI provides a lightweight interface for AI Agents to perform tasks and retrieve knowledge about Android development. However, there's benefits to specialization — Android Studio contains over a decade of Android expertise, built to handle even the most complex Android projects. This includes Android Studio's powerful static analysis engine, refactoring tools, dependency management, UI design and rendering libraries, and more. AI Agents can now tap into Android Studio's tools to gain many of these same capabilities.

The latest version of Android CLI introduces the new android studio command. This enables the agent of your choice to leverage the deep, contextual capabilities of Android Studio to better understand and perform actions on an open Android project. By running Android Studio alongside your preferred agent with Android CLI, your agent’s tasks can more efficiently navigate the codebase to produce more precise code changes. And, when you use Android CLI to create and iterate on your project, transitioning to Android Studio is much easier, so that you can use the purpose built tools—such as, performance profilers, Compose Previews, and Android Device Streaming—to get that production-grade polish.

When you have a project open in the latest preview version of Android Studio Quail, you (or your agent) can run the following command to check whether Android CLI has a connection established with your open project:

$ android studio check
pid: 32942
version: Android Studio
Projects:
    READY     JetSet /Users/adarshf/AndroidStudioProjects/jetset-main

From there, the agents can use the android studio command to access powerful IDE tools to interact with projects more efficiently. Key commands include:

• analyze-file: Analyzes a file for errors and warnings using the editor's built-in inspections.
• find-declaration: Finds the exact definition site of a symbol (class, method, variable, field, constant, or Android resource/color) across the project using semantic resolution.
• find-usages: Finds all references and declarations of a symbol (class, method, variable, or Android resource) across the entire project using semantic analysis.
• render-compose-preview: Renders a Jetpack Compose UI Preview and returns a path to the image and UI hierarchy if successful.
• version-lookup: Get the latest information about which versions for specified app dependencies are available in common repositories, such as the Google Maven repository. By providing a programmatic solution, dependency management is less tedious and much less prone to flakiness.
• open-file: Opens a file directly in Android Studio. This is useful if the agent wants to direct your attention to view Compose Previews, performance traces, or other specific files in the IDE.

For example, agents can now run the following commands to render a Compose preview for a new layout for your Android app, and then open the previews in Android Studio for you to take advantage of seeing multiple Compose Previews side by side and make AI-assisted edits right from the IDE.

$ android studio find-declaration HotelDetailScreen
$ android studio analyze-file .../JetPacker/feature/detail/src/main/java/com/example/jetset/feature/detail/HotelDetailScreen.kt
$ android studio open-file feature/detail/src/main/java/com/example/jetset/feature/detail/HotelDetailScreen.kt

To learn more about how to use these commands, run android help. And, to make sure your agents understand how to work with this tool, make sure to update the Android CLI skill by running android init.

More ways to get started

To make integrating Android CLI into your environments as seamless as possible, we’re making it available in more ways. You can now download and install Android CLI using more package managers: apt-get, winget, and homebrew. For example, you can run the following to install Android CLI using winget:

winget install -e --id Google.AndroidCLI

We’ve also updated the installation to a user-local directory, by default. You can find the commands for all supported operating systems plus additional download options on the Android CLI page.

Support for Journeys

(sped up) An agent running a Journey it generated for an app.

Expanding Android skills

To help models better understand and execute specific patterns that follow our best practices, we are continuing to expand our library of Android skills. We’re shipping new skills that make Android development everywhere more capable, efficient, and productive:

• Display Glasses and Jetpack Compose Glimmer for XR: Provides guidelines for developing projected applications for Android Display Glasses using the Jetpack Compose Glimmer UI toolkit.
• Migration to CameraX: Helps you migrate legacy Android camera implementations (Camera1 or raw Camera2 APIs) to CameraX.
• Perfetto SQL: Translates natural language data prompts into Perfetto SQL queries and executes them against a local trace file.
• Adaptive UI: Instructions to make or update an app's UI so that it adapts to different Android devices
• Testing setup: Creates a basic testing strategy.
• Styles: Helps with adoption of the new Jetpack Compose Style API for new components, and supports migration to Styles API. 
• AppFunctions: Analyzes Android codebases to recommend and implement new AppFunctions, and refines KDoc documentation for Model Context Protocol optimization.

You can add these new skills to your workflow directly from the command line. To help your agents understand and use Android CLI right away, you can initialize your environment and install the base android-cli skill by running:

android init

From there, you can browse and set up your agent workflow by searching for the exact capabilities your agent needs:

android skills list

Once you've found the right skill, install it to your environment by running:

android skills add –skill=<skill-name>

Get started today

To download the stable 1.0 release of the Android CLI, explore the new tools, and browse the complete documentation, head over to d.android.com/tools/agents today!  Also, make sure you update to the latest preview version of Android Studio to unlock the latest features that Android CLI offers. We can't wait to see what you build with Android CLI 1.0 and how these new features supercharge your daily workflows. Join our vibrant community on LinkedIn, Medium, YouTube, or X and  share your feedback.

Explore this announcement and all Google I/O 2026 updates on io.google.

Source: Android Developers Blog

The Android XR ecosystem is expanding, and we’re committed to supporting developers who will build its next great experiences. Today, we’re opening applications for the Android XR Developer Catalyst Program, a dedicated initiative to accelerate the development of Android XR apps ready to launch within the next year.

This program is designed to provide the resources, hardware, and grants to help you build and scale innovative experiences across wired XR glasses, like XREAL’s Project Aura, and intelligent eyewear (audio and display glasses). We are especially interested in seeing innovative experiences across media, gaming, productivity, and health, but we welcome any unique use case that helps users expand what's possible.

Why join the catalyst program?

We want to help developers navigate common barriers to entry for XR development by providing:

• Development Kits: Get early access to hardware development kits for wired XR glasses (XREAL’s Project Aura) and / or intelligent eyewear (audio and display glasses).

• Technical support: Gain access to specialized technical resources and support forums specifically designed to help you prepare your app for Google Play.

• Grant Opportunities: Submit a request and you may be eligible to receive a non-recoupable grant to accelerate your development.

Ready to start building?

Applications are open to developers looking to publish apps for the Android XR ecosystem in the next 6-12 months. You can build with Kotlin and the Jetpack XR SDK, or with Unity, Unreal Engine or Godot. If you need a spark of inspiration, you can check out existing XR Experiments and Samples to see how you can use the SDK for everything from spatial music to navigation.

Once you have your concept ready, be sure to submit your application by June 30th by 11:59PM PDT. We can’t wait to see what you build.

Start Your Application

Explore this announcement and all Google I/O 2026 updates on io.google.

Source: Android Developers Blog