Other

项目介绍

Rohithdgrr/RAY-AI-application 是一个托管在 GitHub 上的开源项目,主要使用 Java 编写,采用 Other 许可证,目前获得 2 个 Star、0 次 Fork。

仓库全名
Rohithdgrr/RAY-AI-application
开源许可证
Other
Star 数
2

README 摘要

RAY AI - Offline AI Inference for Android RAY AI is a high-performance, private, and secure offline AI assistant for Android. It leverages llama.cpp and ONNX Runtime to provide state-of-the-art LLM inference directly on your device without requiring an internet connection. 🚀 Features 100% Offline Inference: No data leaves your device. Private by design. llama.cpp Integration: High-performance C++ backend optimized…

完整内容见 GitHub 原始 README 或本页 。

常见问题

RAY-AI-application 用什么语言开发?

主要使用 Java 编写,采用 Other 许可证,目前有 2 个 Star。

RAY-AI-application 可以免费商用吗?

仓库标注的许可证为 Other,商用前请先阅读仓库 LICENSE 文件确认授权范围。

如何获取 RAY-AI-application 的源码?

可以直接克隆仓库:git clone https://github.com/Rohithdgrr/RAY-AI-application.git,默认分支为 main;安装与运行步骤见仓库 README。

RAY-AI-application 最近还在维护吗?

仓库最近一次更新为 3月19日,当前没有未关闭的 Issue;Star 数为 2,可作为社区活跃度的参考。

关于

GitHub 原始描述(英文)

RAY AI is a high-performance, private, and secure offline AI assistant for Android. It leverages llama.cpp and ONNX Runtime to provide state-of-the-art LLM inference directly on your device without requiring an internet connection.

描述取自 GitHub 官方 API,保持仓库作者书写的原文。

简要分析

热度分
2
价值分
1
活跃状态
活跃

语言占比

C++
CMake
Java

Release

README

image

RAY AI - Offline AI Inference for Android

RAY AI is a high-performance, private, and secure offline AI assistant for Android. It leverages llama.cpp and ONNX Runtime to provide state-of-the-art LLM inference directly on your device without requiring an internet connection.

🚀 Features

  • 100% Offline Inference: No data leaves your device. Private by design.
  • llama.cpp Integration: High-performance C++ backend optimized for mobile ARM processors.
  • Dual Engine Support: Supports both GGUF (via llama.cpp) and ONNX models.
  • Modern Copilot UI: Commercial-grade Material 3 design with smooth animations.
  • Model Management: Download and manage lightweight models optimized for mobile (TinyLlama, Qwen, etc.).
  • Real-time Streaming: Watch responses generate token-by-token.
  • Secure Storage: Models and sensitive data are protected with hardware-backed encryption.

Screenshots

Here’s how RAY AI looks in action:

Chat interface - Thinking phase Model management screen
Response starting Full streaming response

From left to right, top to bottom:
Chat · Model management · Thinking → Response · Complete answer streaming

🛠 Tech Stack

  • Language: Java / C++ (JNI)
  • UI Framework: Android Material Components 3
  • Inference Engines:
  • Build System: CMake & Gradle
  • Min SDK: Android 24 (Nougat)

📥 Getting Started

Prerequisites

  • Android Studio Koala or newer
  • Android NDK 26.1.10909125+
  • CMake 3.22.1+

Installation

  1. Clone the repository:
    git clone https://github.com/Rohithdgrr/working-RAY-AI.git
    
  2. Open the project in Android Studio.
  3. Sync project with Gradle files.
  4. Build and run on a physical device (arm64-v8a recommended).

📄 Documentation

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📜 License

This project is licensed under the MIT License - see the LICENSE file for details.

评论

暂无评论