Firebase Ai Logic
Wire Gemini into a Firebase web or mobile app with client SDKs instead of rolling your own AI backend.
Overview
Firebase AI Logic is an agent skill for the Build phase that integrates Firebase client SDKs with Gemini (Developer or Vertex) for gen-AI in web and mobile apps.
Install
npx skills add https://github.com/firebase/agent-skills --skill firebase-ai-logicWhat is this skill?
- Chooses Gemini Developer API by default and Vertex AI Gemini only when scale or enterprise readiness requires Blaze.
- Covers setup, multimodal inference, structured output, and security for client-side SDK calls without a dedicated AI ser
- Requires Node.js 16+ and npm for web workflows; routes Android, iOS, Flutter, or Web before implementation.
- Documents evolution from Vertex AI for Firebase to Firebase AI Logic for mobile and web developers.
- Points unsupported platforms to official Firebase AI Logic get-started documentation.
- Supports two Gemini API providers: Gemini Developer API and Vertex AI Gemini API
- Prerequisites include Node.js 16+ and npm for web-oriented setup
Adoption & trust: 34.1k installs on skills.sh; 345 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want Gemini in a Firebase app but are unsure which API provider, SDK path, and security setup to use without building a custom backend.
Who is it for?
Indie developers already on Firebase who need documented Gemini Developer vs Vertex tradeoffs and client-side integration steps.
Skip if: Teams not using Firebase, server-only LLM stacks with no client SDK, or one-off scripts that bypass Firebase AI Logic entirely.
When should I use this skill?
Integrating Firebase AI Logic (Gemini API) into web or mobile apps: setup, multimodal inference, structured output, and security.
What do I get? / Deliverables
You get a provider-aligned Firebase AI Logic setup with initialization, inference patterns, and security guidance ready to implement on your target platform.
- Platform-appropriate Firebase AI Logic initialization and SDK usage pattern
- Provider selection (Developer vs Vertex) aligned to prototype vs production needs
- Security-conscious client-side inference configuration notes
Recommended Skills
Journey fit
Canonical shelf is Build → Integrations because the skill is about connecting Firebase AI Logic and Gemini providers into an existing product codebase. Subphase integrations matches third-party SDK setup, provider choice (Gemini Developer vs Vertex), and secure client-side inference—not greenfield UI or pure backend CRUD.
How it compares
Use this official integration skill instead of copying generic Gemini REST examples that ignore Firebase auth, billing, and client SDK guardrails.
Common Questions / FAQ
Who is firebase-ai-logic for?
Solo and small-team builders adding Gemini to Firebase-backed web, Android, iOS, or Flutter apps who want SDK-first setup rather than self-hosted inference.
When should I use firebase-ai-logic?
During Build → Integrations when you are wiring multimodal or structured Gemini calls, picking Developer vs Vertex API, or hardening client-side AI before ship.
Is firebase-ai-logic safe to install?
Review the Security Audits panel on this Prism page and treat any network or API credentials in your repo as secrets you manage; the skill guides Firebase patterns but does not replace your threat model review.
SKILL.md
READMESKILL.md - Firebase Ai Logic
# Firebase AI Logic Basics ## Overview Firebase AI Logic is a product of Firebase that allows developers to add gen AI to their mobile and web apps using client-side SDKs. You can call Gemini models directly from your app without managing a dedicated backend. Firebase AI Logic, which was previously known as "Vertex AI for Firebase", represents the evolution of Google's AI integration platform for mobile and web developers. It supports the two Gemini API providers: - **Gemini Developer API**: It has a free tier ideal for prototyping, and pay-as-you-go for production - **Vertex AI Gemini API**: Ideal for scale with enterprise-grade production readiness, requires Blaze plan Use the Gemini Developer API as a default, and only Vertex AI Gemini API if the application requires it. ## Setup & Initialization ### Prerequisites - Before starting, ensure you have **Node.js 16+** and npm installed. Install them if they aren’t already available. - Identify the platform the user is interested in building on prior to starting: Android, iOS, Flutter or Web. - If their platform is unsupported, Direct the user to Firebase Docs to learn how to set up AI Logic for their application (share this link with the user https://firebase.google.com/docs/ai-logic/get-started) ### Installation The library is part of the standard Firebase Web SDK. `npm install -g firebase@latest` If you're in a firebase directory (with a firebase.json) the currently selected project will be marked with "current" using this command: `npx -y firebase-tools@latest projects:list` Ensure there's at least one app associated with the current project `npx -y firebase-tools@latest apps:list` Initialize AI logic SDK with the init command `npx -y firebase-tools@latest init # Choose AI logic` This will automatically enable the Gemini Developer API in the Firebase console. More info in [Firebase AI Logic Getting Started](https://firebase.google.com/docs/ai-logic/get-started.md.txt) ## Core Capabilities ### Text-Only Generation ### Multimodal (Text + Images/Audio/Video/PDF input) Firebase AI Logic allows Gemini models to analyze image files directly from your app. This enables features like creating captions, answering questions about images, detecting objects, and categorizing images. Beyond images, Gemini can analyze other media types like audio, video, and PDFs by passing them as inline data with their MIME type. For files larger than 20 megabytes (which can cause HTTP 413 errors as inline data), store them in Cloud Storage for Firebase and pass their URLs to the Gemini Developer API. ### Chat Session (Multi-turn) Maintain history automatically using `startChat`. ### Streaming Responses To improve the user experience by showing partial results as they arrive (like a typing effect), use `generateContentStream` instead of `generateContent` for faster display of results. ### Generate Images with Nano Banana - Start with Gemini for most use cases, and choose Imagen for specialized tasks where image quality and specific styles are critical. (Example: gemini-2.5-flash-image) - Requires an upgraded Blaze pay-as-you-go billing plan. ### Search Grounding with the built in googleSearch tool ## Supported Platforms and Frameworks Supported Platforms and Frameworks include Kotlin and Java for Android, Swift for iOS, JavaScript for web apps, Dart for Flutter, and C Sharp for Unity. ## Advanced Features ### Structured Output (JSON) Enforce a specific JSON schema for the response. ### On-Device AI (Hybrid) Hybrid on-device inference for web apps, where the Firebase Javascript SDK automatically checks for Gemini Nano's availability (after installation) and switches between on-device or cloud-hosted prompt execution. This requires specific steps to enab