Aion Ui is a free, local GUI for multiple terminal AI agents (Gemini CLI, Claude Code, Qwen Code, Codex, etc.) with multi-agent chat, persistent conversations, and WebUI remote control. It supports multi-model backends, OAuth/API-key auth, and smart network detection.
It manages MCP servers with discovery/testing, rotates API keys, and bundles tools for file management, Excel/Office tasks, and image generation using Gemini 2.5 Flash and other models. Cross-platform installers ship for Linux and Windows.
Use Cases:
Transform your command-line experience into a modern, efficient AI Chat interface.
English | 简体中文 | 日本語 |Official Site | Twitter
Seamlessly integrate multiple terminal AI agents - Gemini CLI, Claude Code, Qwen Code, Codex and more
Intelligent image generation, editing, and recognition powered by Gemini 2.5 Flash Image Preview - the most advanced image model, with support for other leading AI image models
💡 Need help setting up free image generation? Follow the tutorial to configure image generation models (https://github.com/iOfficeAI/AionUi/wiki/AionUi-Image-Generation-Tool-Model-Configuration-Guide) - Complete step-by-step guide for OpenRouter setup and free Gemini 2.5 Flash Image Preview configuration.
Batch renaming, auto organization, smart classification, file merging
AI helps you create, organize, analyze, and beautify Excel files
Multiple conversations, no task confusion, independent memory, double efficiency
Remote Control Your AI Assistant - Access AionUi from any device on your network! Securely control your local Agent with data staying on your device
💡 Perfect for Server Deployment - Run AionUi 24/7 on Linux servers without desktop environment and access it remotely from anywhere!
This is just the tip of AionUi's capabilities! 🚀
Want to explore more features? Keep reading to discover what else AionUi can help you with:
While the official Gemini CLI is powerful, its command-line interface has limitations for daily use. AionUi provides a GUI alternative that addresses these key pain points:
- Using the
@command to select files is cumbersome- Conversations are lost when closing the CLI window
- Command-line interface lacks natural chat interactions
- Single conversation mode limits parallel workflows
- Restricted to Gemini models only, unable to use other excellent large language models
AionUi provides a modern interface for users who need better workflow efficiency, while breaking the single-model limitation, allowing you to choose the most suitable AI model for different task requirements.
Ready to try AionUi? Download the latest version for your platform from our releases page:
💡 Need detailed configuration guide? Check our Complete Installation Tutorial (https://github.com/iOfficeAI/AionUi/wiki/Getting-Started)
Want to hack on AionUi?
npm installnpm startDuring npm start, Electron Forge spins up two ports:
Override them via env vars when needed:
AIONUI_DEV_PORT=3100 \
AIONUI_LOGGER_PORT=9100 \
npm start
<!-- truncated for length -->
GPU-accelerated, non-destructive RAW image editor built with Rust/Tauri/React, offering fast previews, masking, and color grading with a performance-first workflow.
Local, privacy-first AI workspace that bundles chat, code, image generation, agents, and automation in one app using local Llama.cpp models with tool-calling and MCP integration.
5MB Rust OpenAI-compatible server for local GGUF/SafeTensors models with hot swaps, auto-discovery, and optional GPU/MOE offloading for drop-in use across tools and SDKs.
Tiny Rust OpenAI-compatible server for local GGUF/SafeTensors models with hot swaps, auto-discovery, and multi-backend GPU/MOE support for drop-in use across editors and SDKs.
803KB pure-C Windows timer with clock/countdown/Pomodoro modes, animated tray icons, transparent always-on-top UI, and portable winget install.
AI agent context platform with natural role switching, MCP-based tool integration, and desktop/Docker deployments for Claude/Cursor and other AI apps.