AionUi - Free, Open-Source Desktop Office Agent

• Official Website: https://www.aionui.com
• GitHub Repository: https://github.com/iOfficeAI/AionUi
• Download Address: https://github.com/iOfficeAI/AionUi/releases

Core Features

💬 Multi-Session Chat

• Multi-Session + Independent Context - Open multiple chat sessions simultaneously, each session has independent context memory
• Local Storage - All conversation data is saved in a local SQLite database and will not be lost

🤖 Multi-Model Support

• Multi-Platform Support - Supports mainstream models like Gemini, OpenAI, Claude, Qwen, flexible switching
• Local Model Support - Supports local model deployment like Ollama, LM Studio

🤝 Multi-Agent Mode

• Run Multiple AI Agents Simultaneously - Can run multiple AI agents simultaneously (such as Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, etc.)
• MCP Unified Management - Unified management and configuration of all agents through Model Context Protocol (MCP), simplifying operations
• Skills Configuration - Support configuring dedicated Skills for different agents to extend agent capabilities
• Assistant Customization - Support custom assistant configuration to create personalized AI workflows
• Independent Configuration - Each agent can be configured and used independently without interference
• Flexible Switching - Flexibly switch between different agents to meet various scenario needs

🗂️ File Management

• File Tree Browsing + Drag & Drop Upload - Browse files like folders, support drag and drop files or folders for one-click import
• Smart Organization - Let AI help organize folders with automatic classification

📄 Preview Panel

• 9+ Format Preview - Supports PDF, Word, Excel, PPT, code, Markdown, images, and other formats
• Real-time Tracking + Editable - Automatically tracks file changes, supports real-time editing and debugging of Markdown, code, HTML

🎨 AI Image Generation & Editing

• Intelligent Image Generation - Supports multiple image generation models like Gemini 2.5 Flash Image Preview, Nano, Banana
• Image Recognition & Editing - AI-driven image analysis and editing features

🌐 Multi-Channel Access

• WebUI Remote Access - Access from any device on the network via browser, supports mobile devices
• Telegram Integration - Support interaction through Telegram bot
• Feishu Integration - Support access and interaction through Feishu
• Local Data Security - All data stored in local SQLite database, suitable for server deployment

Nova Router Configuration Steps

1. Copy the API key from Nova Router

2. Open AionUi Settings

   • Enter the settings page in AionUi
   • Find the Model Configuration Tab
   • Click "Add Model"

   

3. Add New Provider

   • Click "Add Model"
   • Select Nova Router

4. Configure API Information

   • API Address: Fill in your Nova Router site address (format: https://<your-service-domain>/v1)
   • API Key: Paste the API Key copied from the Nova Router console

5. Add Models

   • Select the model to add from the dropdown
   • Model name should match the model name configured in Nova Router
   • Select the appropriate request protocol

6. Start Using

   • Return to the chat page
   • Select the configured Nova Router model to start a conversation

How to confirm it worked

• The provider or model appears in the AionUi model list
• You can fetch or manually enter model names successfully
• You can select the model in chat and start a conversation normally

Related Links

• GitHub Repository
• Complete Usage Guide
• FAQ