Ayna

A native agentic AI client for macOS, iOS, and watchOS, built with SwiftUI.

Screenshots

Multi-provider models	Built-in and MCP tools
Agent permissions	Memory

Features

• 💬 Fast & Native: Streaming chat interface tailored for Apple platforms.
• ☁️ Multi-Provider: Native support for OpenAI, Anthropic, and Azure OpenAI. Also works with any OpenAI-compatible endpoint (Gemini, Ollama, etc.).
• 🔀 Multi-Model Chat: Compare responses from multiple models simultaneously.
• 🍎 Apple Intelligence: Uses the on-device Apple Intelligence API when available (macOS/iOS).
• 🏠 Local Models: Connect to local servers like Ollama via custom endpoint.
• 🛠️ MCP Support: Use Model Context Protocol (MCP) tools.
• 🎨 Image Generation: Create images using models like gpt-image-1.
• 🧠 Memory: Remember facts across conversations with natural language commands.
• 🗂️ Organization: Searchable conversations with auto-generated titles.
• 🔒 Secure: API keys stored in Keychain; conversations encrypted on disk.
• 📝 Export: Save chats as Markdown or PDF.
• ⌚ watchOS Companion: Quick chat access from your Apple Watch.

Getting Started

Installation

1. Grab the latest .dmg from the Releases page.
2. Open the disk image and drag Ayna.app into your Applications folder.
3. App is quarantined because it's not notarized. To remove the quarantine, run this command in Terminal:

xattr -dr com.apple.quarantine /Applications/Ayna.app

4. Launch Ayna from Applications.

Homebrew

You can also install Ayna via Homebrew:

brew tap sozercan/ayna
brew install --cask ayna

Requirements

• macOS 26.0 (Tahoe) or newer, iOS 26.0 or newer, or watchOS 26.0 or newer.
• An API key for OpenAI, Anthropic, or Azure OpenAI (optional if using local models).

User Guide

Connect to AI Providers

1. Open Settings (Cmd+,) → Models.
2. Select your provider and add a model:
   • OpenAI: Use the default endpoint or a custom OpenAI API-compatible endpoint.
   • Anthropic: Use the default endpoint or a custom Anthropic API-compatible endpoint.
   • Azure: Use https://<resource>.openai.azure.com (Azure OpenAI) or https://<resource>.services.ai.azure.com (Microsoft Foundry) with your deployment name as the model.
   • Apple Intelligence: For on-device inference.
3. Start chatting!

Multi-Model Chat

1. Start a New Chat (Cmd+N).
2. In the model selector, choose multiple models (e.g., GPT-4o and Claude 3.5 Sonnet).
3. Send your prompt.
4. Ayna will stream responses from all selected models in parallel, allowing you to compare their outputs side-by-side.

Enable Tools (MCP)

1. Go to Settings → Tools.
2. Add an MCP server to give the AI more capabilities.

Keyboard Shortcuts

• Cmd+N: New conversation
• Cmd+,: Open Settings
• Enter: Send message
• Shift+Enter: New line

Privacy

• No Telemetry: We don't track your usage.
• Local Storage: Conversations are encrypted and stored only on your device.
• Secure Keys: API keys are stored securely in the system Keychain.

Contributing

Developers, please see CONTRIBUTING.md for build instructions, architecture details, and testing guidelines.

Support

Found a bug? Open an issue.