📦 Models
Manage AI models, downloads, and deployment
Download Queue
Pending and active downloads
Model Preferences
Default model selection behavior
Default LLM
Model used for general chat
Auto-select by task
Automatically choose best model for task type
🖥️ Nodes
GPU nodes and compute resources on your network
Network Nodes
Discovered compute nodes
Sync Settings
Model syncing between nodes
Auto-sync new models
Automatically rsync models to GPU nodes
Storage node
Primary model storage location
🧤 Gloves
Manage installed gloves, add from GitHub, and check system readiness
System Readiness
Health status of all backend services
Checking systems...
Installed Gloves
Manage your glove collection from the package repository
🌐 API Providers
Configure cloud AI providers and routing
API Keys
Stored securely in environment
OpenAI
GPT-4, o1, DALL-E
Anthropic
Claude 3.5
Google AI
Gemini Pro
💬 Prompts
System prompts and AI behavior customization
System Prompt
Instructions prepended to all conversations
🔧 Tools & MCP
Model Context Protocol servers and tool configurations
MCP Servers
Connected tool servers
Enable tool calls
Allow models to use external tools
🔍 Web Search
RAG and web search configuration
SearxNG
Self-hosted search for RAG
SearxNG URL
Local search instance
Auto-search for context
Search web before responding
🎵 Audio
Text-to-speech and voice settings
TTS Voice
Text-to-speech configuration
Voice
Pitch
Rate
🎨 Display
Visual preferences and themes
Theme
Visual appearance
Dark Mode