aws-samples/sample-mobile-ai-assistant

A lightning-fast, cross-platform mobile AI Assistant App built with React Native.

What it solves

It provides a fast, cross-platform mobile and desktop application that serves as a personal AI workspace. It solves the problem of needing a unified interface to interact with various AI models (like Amazon Bedrock, OpenAI, and Ollama) for chatting, generating images, and creating instant web applications on the go.

How it works

Developed with React Native, the app connects to AI models via API keys or a dedicated App Server (deployed using AWS Lambda and API Gateway for long-duration streaming). It supports multiple providers including Amazon Bedrock, DeepSeek, OpenAI, and Ollama. The app handles multimodal inputs (text, images, video, and documents) and uses a local-first storage approach with react-native-mmkv for high-speed data access.

Who it’s for

Users who want a high-performance, privacy-focused AI assistant on Android, iOS, or macOS that can handle complex tasks like web app generation, real-time web search, and multimodal analysis across different LLM providers.

Highlights

  • Instant Web App Creation: Generate, edit, and share functional web apps (e.g., games like Tetris or News Readers) from a single prompt.
  • Multimodal Capabilities: Supports analysis of text, images, documents, and videos, including 4K video uploads with auto-compression.
  • Broad Model Support: Compatible with Amazon Bedrock, OpenAI, DeepSeek, Ollama, and other OpenAI-compatible APIs.
  • Advanced AI Tools: Includes real-time web search, Mermaid chart rendering, LaTeX support, and AI image generation with a dedicated gallery.
  • Voice Interaction: Features speech-to-speech capabilities with barge-in support and echo cancellation via Amazon Nova Sonic.
  • Performance Optimized: Uses AOT compilation and native components to ensure fast launch and responsive streaming.

Related

  • Project
    aws-samples/amazon-bedrock-client-for-mac

    A native macOS client that provides system-wide quick access to Amazon Bedrock's AI models for text, image, and video generation.

  • Project
    aws-samples/bedrock-chat

    A multilingual generative AI platform powered by Amazon Bedrock that enables the creation, sharing, and management of custom RAG-enabled bots and AI agents.

  • Project
    dabit3/react-native-ai

    A full-stack framework for building cross-platform mobile AI apps with built-in support for real-time LLM streaming and image generation.

  • Project
    google-ai-edge/gallery

    A mobile and macOS application for running open-source LLMs locally on-device, providing a private and offline environment to experience and evaluate generative AI.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.