Firebase

Building for the Apple ecosystem? You will soon be able to securely call cloud-hosted Gemini models directly from Apple’s Foundation Models framework 🔥 This integration, powered by Firebase AI Logic, will allow you to use both Apple’s Foundation Models and Gemini models via a shared API surface.

⚡ Agent Skills now includes Crashlytics and Remote Config, making it easier to set up and use these products with agentic assistance. Crashlytics skills enable debugging assistance inside IDEs so you can resolve issues faster, without interrupting your coding or requiring you to switch to viewing the Crashlytics dashboard. Docs: goo.gle/42SvfDb

Location services for your app with Gemini and Firebase AI Logic 📍 Learn how to add Google Maps Grounding to Gemini queries to get better results. Chapters: 0:00 - Introduction 0:40 - Demo 1:25 - How to add Google Maps grounding

Come to the AiOS meetup today to learn how to use Gemini in Apple's Foundation Model framework via @Firebase AI Logic! Show me an app you've built with this new integration, and win some rare Firebase swag!

The @Firebase AI Logic Hybrid API provides a single, unified interface for splitting inference between cloud and on-device environments. Hybrid inference lets you easily route AI requests to the models running on-device and in the cloud, optimizing performance, cost, and availability → goo.gle/3PrmGw5

Excited to integrate Gemini models into your iOS app directly from Apple’s Foundation Models framework via Firebase? This video walks you through setup and integration, and three use cases in the Landmarks sample app → goo.gle/3PSzcF5 ➕ Grounding with Google Maps ➕ Landmark Detail with Search Grounding ➕ Visual Landmark Discovery

You can now securely call the Gemini API from your Swift app using Apple’s Foundation Models framework. Read the blog to see the shortest path from zero to a working Gemini call, and explore what you can build beyond text, including real-world grounding, multimodal input, and agentic tool calling → goo.gle/4443d81

You will be able to easily swap between local and cloud inference, giving you flexibility to enable optimal agentic app experiences for your use case. Learn more about this partnership announced at #WWDC26: goo.gle/4ulNzja

Building for the Apple ecosystem? You will soon be able to securely call cloud-hosted Gemini models directly from Apple’s Foundation Models framework 🔥 This integration, powered by Firebase AI Logic, will allow you to use both Apple’s Foundation Models and Gemini models via a shared API surface.

🔥🍏

Build a full-stack application with Kiro and Firebase → goo.gle/43Ra18U In this video, you'll learn how to build fast with Firebase Agent Skills in Kiro. We'll also cover best practices and live coding examples.

Bring agentic voice and video experiences to your apps with Firebase AI Logic ⚡️ Discover how to connect your frontend directly to the Gemini Live API and implement function calling via Firebase AI Logic, all while helping to keep your resources protected with App Check! Get the details → goo.gle/4emfivk

Live search is a great way to let users find things quickly in your app, and with new text search support in Firestore Enterprise and modern React APIs, it doesn’t take much code to implement. 🔍 Learn more about implementing search in a React web app → goo.gle/49t0Qiw

See the release notes here: goo.gle/4e0eew0

Hybrid inference for Chrome is now GA 🎉 We've also added initializeDeviceModel() method, which must be called explicitly to initialize the on-device model before making any on-device inference calls.

🎣 Catch all the updates from Firebase at #GoogleIO in this month's Firebase Release Notes! Chapters: 0:23 - Firebase integration with Antigravity and Android Studio 1:19 - Agent Skills for Firebase now cover mobile development 2:17 - Firebase powers new Google AI Studio features 2:38 - Firebase AI Logic new models and features 5:40 - Firebase full-stack template in App Design Center 6:12 - Crashlytics for web is coming soon

We’ve had a lot of updates to Firebase AI Logic lately! 🚀 Dive into our new video to learn how to leverage them and ship AI features with confidence → goo.gle/3RxFri2 Discover how to help secure prompts with Server Prompt Templates, explore demos of AI Logic-triggered Cloud Functions, and run workloads across platforms with hybrid inference. Plus, learn how to use AI monitoring and context caching to scale smoothly.

Android developers can now use Agent Mode in Android Studio and get Agent Skills for Firebase with no additional setup 😌 Your agent will be able to set up Firestore and Firebase Authentication, generate code for Firestore, and even write security rules! Learn more about updates to Android Studio → goo.gle/4nPp9wR

Unlock the next level of data power with Firestore Enterprise edition 🔓💪 Learn how to utilize the most requested features in Firestore including native full text search, joins (subqueries), and pipeline operations → goo.gle/4wRxggJ

Welcome back to Code, Commit, Deploy, Repeat! Tune in LIVE: goo.gle/4uEnQn8 This time, Peter and Marina will implement a brand-new AI feature using Firebase AI Logic and Gemini that allows users to automatically break down larger work items (such as planning a party or a trip) into smaller, actionable subtasks.

Now available via Firebase AI Logic 🍌😎