gallery

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

19 articles 17.4k View on GitHub ↗
19 articles
How to Extend Mobile Actions with Custom Native Functionality: A Step-by-Step Guide

Extend Mobile Actions with custom native functionality. Learn how to annotate Kotlin methods, define Action subclasses, and implement Android logic step-by-step. Enhance your mobile app development now.

how-to-guide
Apr 6, 2026
Build System Used for the Android App in AI Edge Gallery: Gradle with Kotlin DSL

Discover the Gradle Kotlin DSL build system powering the Google AI Edge Gallery Android app. Learn about its centralized configuration, version catalog, and SDK 35 Jetpack Compose setup.

internals
Apr 6, 2026
Minimum Android and iOS Versions Required for the Google AI Edge Gallery App

Discover the minimum Android 12+ and iOS 17+ OS versions needed for the Google AI Edge Gallery app. Learn why these requirements ensure access to the latest ML APIs.

api-reference
Apr 6, 2026
How Google AI Edge Gallery Maintains Privacy and Security During On-Device Inference

Discover how Google AI Edge Gallery secures on-device inference. Learn about LiteRT-LM runtime, private app directories, and local tensor processing for complete user privacy.

best-practices
Apr 6, 2026
How to Add Tool Definitions for Mobile Actions in Android

Learn how to add tool definitions for Mobile Actions in Android by annotating Kotlin functions and implementing execution logic. Follow our guide for seamless integration.

how-to-guide
Apr 6, 2026
How to Define New Action Types for Mobile Actions in Google AI Edge Gallery

Learn how to define new action types for Mobile Actions in the Google AI Edge Gallery. Extend ActionType, expose a matching Tool method, and implement runtime logic.

how-to-guide
Apr 6, 2026
How to Use the 'Ask Image' Feature for Visual Analysis with the Device Camera in Google AI Edge Gallery

Unlock visual analysis with the 'Ask Image' feature in Google AI Edge Gallery. Use your device camera to query on-device LLMs for insights without cloud data. Learn more today.

how-to-guide
Apr 6, 2026
Google AI Edge Gallery Multimodal Capabilities: On-Device Image and Audio Processing

Explore multimodal capabilities in the Google AI Edge Gallery. Process images and audio on-device with Ask Image and Audio Scribe tasks for LLMs.

deep-dive
Apr 6, 2026
How to Load Agent Skills from URLs or Community Contributions in AI Edge Gallery

Learn to load Agent Skills from URLs or community contributions in the AI Edge Gallery. Easily add new skills using SkillManagerViewModel and SkillAllowlist.

how-to-guide
Apr 6, 2026
How to Embed JavaScript and HTML in Google AI Edge Gallery Agent Skills

Learn to embed JavaScript and HTML in Google AI Edge Gallery Agent Skills. Build interactive web interfaces for LLM tool calls using native webviews.

how-to-guide
Apr 6, 2026
How Agent Skills Extend LLMs with External Integrations in Google AI Edge Gallery

Learn how Agent Skills extend LLMs with external integrations securely on device. Inject metadata and route tool calls to JavaScript or Android for powerful, cloud-free assistants. Explore Google AI Edge Gallery.

deep-dive
Apr 6, 2026
How to Perform Benchmark Testing of Models on Different Hardware in the Gallery App

Benchmark test AI models on various hardware using the Gallery app. Measure init latency, prefill throughput, and decode speed. Compare results efficiently.

how-to-guide
Apr 6, 2026

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:
curl -s "https://instagit.com/install.md"
Works with
Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →