v1.0.0

🎉 Xirea v1.0.0

I'm excited to announce the first stable release of Xirea — a modern, privacy-focused desktop AI assistant that lets you chat with local GGUF models or your favorite cloud AI providers from a beautiful native desktop application.

✨ Highlights

• 🤖 Local AI inference powered by llama.cpp

• 🧠 Support for GGUF models (Qwen, Llama, Gemma, Mistral, and more)

• ☁️ Connect to popular cloud providers:

  • OpenAI
  • Anthropic
  • Google Gemini
  • Groq
  • Mistral
  • OpenRouter
  • Azure OpenAI

• 💬 Clean multi-conversation chat interface

• 📁 Bring your own local models

• 🔒 Privacy-first architecture — your local chats stay on your device

• ⚡ Native desktop application built with Tauri + React

📦 Downloads

Choose the installer for your operating system:

• Windows (x64) → .msi
• macOS (Apple Silicon) → .dmg
• macOS (Intel) → .dmg
• Linux (Debian/Ubuntu) → .deb
• Linux (Universal) → .AppImage

🛠️ Tech Stack

• Tauri 2
• React
• TypeScript
• Rust
• llama.cpp
• Tailwind CSS

⚠️ Requirements

Local Models

To use local AI, download any supported GGUF model and load it from within Xirea.

Recommended lightweight models include:

• Qwen 2.5
• Gemma 3
• Llama 3.x
• Mistral

Cloud Providers

For cloud inference, configure your own API keys in the application's settings.

❤️ Privacy

Xirea does not upload your local conversations or models unless you explicitly choose to use a cloud provider.

Your local models remain on your computer.

🐞 Reporting Issues

If you encounter a bug or have a feature request, please open an issue:

https://github.com/Danyalkhattak/Xirea-Desktop/issues

🚀 What's Next

Future releases will focus on:

• Model management
• Document and file chat
• RAG support
• Plugin ecosystem
• Better performance
• Additional providers
• Quality-of-life improvements

---

Thank you for trying Xirea and supporting the project! 💙