orailnoor/cross-platform-llm-client

A unified cross-platform AI client supporting seamless transitions between standard cloud APIs and on-device, offline execution of custom and uncensored language models.

What it solves

PrivateLM provides a unified, cross-platform interface for interacting with AI models, solving the dilemma between privacy-focused local execution and the power of cloud-based LLMs. It allows users to run models entirely on-device to ensure data privacy or switch to cloud APIs for more complex tasks.

How it works

Built with Flutter, the app uses a dual-inference pipeline. For local execution on Android and iOS, it wraps llama.cpp (via llama_flutter_android) to run GGUF models with GPU acceleration (Vulkan on Android, Metal on iOS). For cloud access, it provides a normalized service that connects to OpenAI, Anthropic, Google Gemini, and Kimi APIs. The app automatically detects device RAM to recommend optimal settings and stores all chat history and API keys locally using Hive.

Who it’s for

Users who want a single AI chat client that supports both private, offline local models and high-performance cloud LLMs across Android, iOS, and Web platforms.

Highlights

  • Hybrid Inference: Seamlessly switch between local GGUF models and cloud APIs (OpenAI, Claude, Gemini, Kimi).
  • Hardware Optimized: Automatic RAM detection and GPU acceleration for on-device performance.
  • Multimodal Support: Ability to send text and images, supporting vision models like Qwen2-VL locally.
  • Privacy-First: Local storage of sessions and keys via Hive, ensuring data doesn't leave the device in local mode.
  • Task Management: Includes a dedicated view for structured AI workflows alongside standard chat.

Related

  • Project
    Mobile-Artificial-Intelligence/maid

    An open-source Android application for running LLMs locally via llama.cpp or connecting to remote AI providers like OpenAI and Anthropic.

  • Project
    AtomicBot-ai/Atomic-Chat

    A local AI application and inference engine that lets users run open-weight LLMs privately on their own devices while providing an OpenAI-compatible API for other agents.

  • Project
    Chevey339/kelivo

    Kelivo is a cross-platform Flutter-based LLM chat client that integrates multiple AI providers, web search, and multimodal inputs into a single interface.

  • Project
    netdur/llama_cpp_dart

    A Dart FFI binding for llama.cpp that enables running LLMs, vision, and audio models locally within Flutter apps on iOS and Android.

  • Project
    Vali-98/ChatterUI

    A native mobile frontend for LLMs that allows users to run models on-device using llama.cpp or connect to various commercial and open-source APIs.