This is a modern Android application that demonstrates on-device LLM inference using MediaPipe GenAI and Google AI Edge Local Agents. It features a conversational interface with support for native tool triggering (skills) like web search and calendar viewing.

The app uses Skill.md to declare AI Tools: view_calendar and web_search. SKILLs are placed in feature/chat/src/main/assets chat/util/SkillLoader.kt is used to find and parse Skills.

Follow these steps to set up the project on your local machine.

Download and install the latest stable version Android Studio Quail 1 of Android Studio (Ladybug or newer recommended).

Clone the repository from GitHub or unzip the provided archive into your preferred workspace directory.

The project requires a Hugging Face User Access Token to download models.

1. Generate a token at huggingface.co/settings/tokens ( Read access is sufficient).
2. Open (or create) the local.properties file in the root directory of the project.
3. Add the following line:

   HUGGING_FACE_TOKEN=your_token_here

1. Launch Android Studio.
2. Select Open and navigate to the project root folder.
3. Wait for the Gradle sync to complete.

The project follows a modular architecture:

• :core:coroutines: Base classes and utilities for Kotlin Coroutines and Flow-based UseCases.
• :core:database: Room database implementation for storing chat history.
• :core:di: Koin dependency injection configuration and extensions.
• :core:filestore: Manages file operations in the app's internal and cache directories.
• :core:navigation: Centralized navigation logic using Jetpack Compose Navigation.
• :core:ui: Shared UI components, themes (Material 3), and base ViewModel.
• :core:util: General-purpose utility classes and extensions.

• :feature:home: The main landing screen.
• :feature:chat: The conversational interface, including LLM inference logic and skill parsing.
• :feature:download: Background worker implementation for downloading LLM models from Hugging Face.
• :feature:settings: Application settings and configuration.
• :feature:tooling: Native tool implementations (e.g., Jsoup-based web search, Calendar provider).

• The main entry point that wires all modules together and initializes Koin.

• Jetpack Compose: For a modern, declarative UI.
• MediaPipe GenAI: On-device LLM inference.
• Google AI Edge Local Agents: Structured function calling (skills) protocol.
• Koin: Lightweight dependency injection.
• WorkManager: Reliable background model downloading.
• Jsoup: Web scraping for the search tool.
• OkHttp: For network requests.

1. Connect a physical Android device (recommended) or an emulator.
   • Note: LLM inference is resource-intensive and works best on modern devices (e.g., Pixel 7 or newer).
2. Select the app configuration in Android Studio.
3. Click Run.
4. Upon opening the Chat, the app will automatically start downloading the LLM model (~700MB). You can track the progress on the screen.

1. A new Gemma 4 LLM doesn't work with MediaPipe engine. It requires LiteRT engine (more advanced implementation).
2. Sometimes LLM hallucinates when asking about agenda, view calendar instead of using ' view_calendar' tool

Senior Android Engineer & Tech Partner (10+ yrs)

Specialized in Native Android (Kotlin + Jetpack Compose) and on-device AI/LLM / Google AI Edge.

Need to integrate AI capabilities, local LLMs, or buіld an Android app from 0 to launch?