Welcome to Llumen
Why Llumen?
Most self-hosted AI interfaces are built for servers, not devices. They're powerful but demand heavy resources and hours of configuration.
Llumen carves out a different space: privacy without the complexity. You get the features you actually need, optimized for modest hardware like Raspberry Pi, old laptops, or minimal VPS—while keeping many features of commercial products.
Private
100% local. Your conversations never leave your device.
Lightweight
~17MB binary, <128MB RAM usage
Zero-config
30-second Docker setup. No config files needed.
Quick Comparison
| Privacy | Power | Setup | |
|---|---|---|---|
| Commercial (ChatGPT) | ❌ Cloud-only | ✅ High | ✅ Zero-config |
| Typical Self-Host (Open WebUI) | ✅ Local | ✅ High | ❌ Config hell |
| llumen | ✅ Local | ⚖️ Just enough | ✅ Zero-config |
Key Features
Chat Modes
Normal, Web Search, and Deep Research with autonomous agents
Rich Media
PDF uploads, LaTeX rendering, image generation
Beautiful Themes
Multiple gorgeous mobile-optimized themes
Lightning Fast
Sub-second cold starts, real-time streaming
Get Started
Install
Get llumen running in 30 seconds
Configure
Simple environment variable setup
First Steps
Learn the basics and start chatting
API Providers
Use OpenRouter, local models, and more
Default Login: admin / P@88w0rd (Remember to change this!)