# google-ai-edge/gallery

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/google-ai-edge-gallery).**

15,162 stars · 1,305 forks · Kotlin · apache-2.0

## Links

- GitHub: https://github.com/google-ai-edge/gallery
- awesome-repositories: https://awesome-repositories.com/repository/google-ai-edge-gallery.md

## Description

This project is a development framework for building edge-based AI agents that perform multimodal inference and system-level automation directly on mobile devices. By prioritizing local-first execution, the platform ensures data privacy and offline functionality, allowing developers to run large language models on hardware without requiring external server connectivity.

The framework distinguishes itself through an integrated orchestration layer that connects language models to custom tools, scripts, and native device intents. It provides a structured registry for mapping natural language instructions to executable code, enabling agents to perform proactive tasks, trigger system actions, and interact with local or remote services. To support complex workflows, the platform includes sandboxed script execution and dynamic webview rendering, allowing models to generate and display interactive interfaces within the conversation flow.

Beyond core inference, the system offers comprehensive utilities for managing and benchmarking local model files, including tools for prompt engineering and performance tuning. It also features diagnostic capabilities that visualize the internal reasoning traces of models and provide debugging logs for script execution. The platform is designed with security in mind, incorporating native credential management and repository access controls to maintain compliance while processing sensitive data locally.

## Tags

### Artificial Intelligence & ML

- [Agentic LLM Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-llm-frameworks.md) — Provides a development platform for building and managing autonomous agents powered by local large language models.
- [Local AI Inference](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/local-and-on-device-inference/local-ai-inference.md) — Executes large language models directly on device hardware to ensure data privacy and offline functionality.
- [On-Device Models](https://awesome-repositories.com/f/artificial-intelligence-ml/on-device-models.md) — Enables running large language models directly on mobile hardware to ensure data privacy and offline functionality.
- [AI Agent Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-integrations/ai-agent-tool-integrations.md) — Connects language models to external software modules and custom scripts to enable proactive assistance and task automation.
- [Local Model Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/local-model-execution.md) — Runs open-source large language models directly on device hardware to ensure privacy and offline operation. ([source](https://github.com/google-ai-edge/gallery#readme))
- [Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/on-device-models/agent-orchestrators.md) — Orchestrates the connection between local language models, custom tools, and native device intents for proactive assistance.
- [LLM Tool Calling](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-tool-calling.md) — Maps natural language instructions to executable code modules or system-level intents through a structured registry.
- [Multimodal Inference Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/inference-servers-and-runtimes/multimodal-inference-engines.md) — Processes text, audio, and visual data directly on hardware to enable offline multimodal inference.
- [Agent Skill Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/configuration-and-specifications/agent-skill-definitions.md) — Extends model capabilities by creating modular scripts that provide domain-specific knowledge or specialized tools. ([source](https://github.com/google-ai-edge/gallery/tree/main/skills))
- [Agent Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/agent-tool-integrations.md) — Connects autonomous agents to external software tools and services to extend their functional capabilities.
- [Model Provider Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations.md) — Supports connecting to third-party model providers through configurable authentication and secure download schemes. ([source](https://github.com/google-ai-edge/gallery/blob/main/DEVELOPMENT.md))
- [Audio Transcription](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-transcription.md) — Converts voice recordings into text in real-time using high-efficiency language models running locally. ([source](https://github.com/google-ai-edge/gallery#readme))
- [Proactive Assistance Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/context-augmentation-tools/proactive-assistance-tools.md) — Enables models to connect with external tools and modular skills to provide proactive assistance and verify facts. ([source](https://github.com/google-ai-edge/gallery#readme))
- [Reasoning Transparency Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/reasoning-models/reasoning-transparency-interfaces.md) — Extracts and displays internal model reasoning steps to provide transparency into decision-making processes.
- [Reasoning Process Monitors](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/ai-observability-evaluation/reasoning-process-monitors.md) — Visualizes and audits the step-by-step reasoning chains used by models to provide transparency into complex problem solving. ([source](https://github.com/google-ai-edge/gallery/blob/main/README.md))
- [Multimodal AI Applications](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/multimodal-processing-tools/multimodal-ai-applications.md) — Integrates multiple sensory inputs like audio and visual data to perform real-time analysis and transcription.
- [Prompt Engineering](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-engineering.md) — Provides tools to experiment with prompt variations and adjust model parameters to achieve specific output results. ([source](https://github.com/google-ai-edge/gallery/blob/main/README.md))
- [Remote Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/remote-tool-integrations.md) — Facilitates connecting cloud-hosted services to the local environment using custom authentication headers for secure data access. ([source](https://github.com/google-ai-edge/gallery/tree/main/mcp))
- [AI Model Benchmarking](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/ai-observability-evaluation/ai-model-benchmarking.md) — Provides standardized tests to evaluate the performance and reliability of local machine learning models.
- [Model Abstractions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-abstractions.md) — Manages the secure download and configuration of external model files through standardized authentication and storage management.

### Graphics & Multimedia

- [System-Webview-Based Renderers](https://awesome-repositories.com/f/graphics-multimedia/graphics-engines-rendering/rendering/systems/dom-web-rendering-strategies/system-webview-based-renderers.md) — Displays interactive web-based interfaces within the conversation flow using native webview components.
- [Multimodal Analysis Engines](https://awesome-repositories.com/f/graphics-multimedia/media-processing-analysis/media-manipulation/media-processing-workflows/generative-visual-engines/multimodal-analysis-engines.md) — Processes images from the camera or storage to identify objects and generate detailed descriptions using multimodal models. ([source](https://github.com/google-ai-edge/gallery#readme))

### Operating Systems & Systems Programming

- [System Automation Intents](https://awesome-repositories.com/f/operating-systems-systems-programming/native-system-interfacing/system-automation-intents.md) — Maps model instructions to native device intents and local controls to execute complex system actions.
- [Native System Interfacing](https://awesome-repositories.com/f/operating-systems-systems-programming/native-system-interfacing.md) — Triggers system-level actions by mapping model instructions to platform-specific native capabilities. ([source](https://github.com/google-ai-edge/gallery/tree/main/skills))

### Security & Cryptography

- [Local Data Processing Tools](https://awesome-repositories.com/f/security-cryptography/local-data-processing-tools.md) — Ensures data privacy by performing all model inference and processing entirely on the local device hardware. ([source](https://github.com/google-ai-edge/gallery/blob/main/README.md))
- [Credential Security Managers](https://awesome-repositories.com/f/security-cryptography/credential-security-managers.md) — Manages sensitive access credentials securely via native dialogs to prevent exposure to language models. ([source](https://github.com/google-ai-edge/gallery/tree/main/skills))

### Software Engineering & Architecture

- [Custom Action Handlers](https://awesome-repositories.com/f/software-engineering-architecture/custom-action-handlers.md) — Provides a framework for defining custom logic that models can trigger to perform specific tasks or interact with device features. ([source](https://github.com/google-ai-edge/gallery/blob/main/Function_Calling_Guide.md))
- [Sandboxed Execution Environments](https://awesome-repositories.com/f/software-engineering-architecture/sandboxed-execution-environments.md) — Runs custom logic within isolated environments to process data securely while maintaining system stability.

### Development Tools & Productivity

- [Task Automation Tools](https://awesome-repositories.com/f/development-tools-productivity/task-automation-tools.md) — Executes offline device controls and interactive functions using specialized lightweight models for task-oriented automation. ([source](https://github.com/google-ai-edge/gallery#readme))

### Networking & Communication

- [Local Integration Servers](https://awesome-repositories.com/f/networking-communication/local-integration-servers.md) — Enables connecting external software modules to the local environment to extend model capabilities with custom functions. ([source](https://github.com/google-ai-edge/gallery/tree/main/mcp))

### Programming Languages & Runtimes

- [JavaScript Environments](https://awesome-repositories.com/f/programming-languages-runtimes/runtime-execution-environments/runtime-environments/language-runtimes/javascript-environments.md) — Runs custom JavaScript scripts within the environment to process data or generate interactive content. ([source](https://github.com/google-ai-edge/gallery/tree/main/skills))