Web UI

llms.py includes a modern, fast, and privacy-focused web interface that provides a ChatGPT-like experience for accessing all your local and remote LLMs.

Overview

The UI is built with simplicity and privacy in mind:

• No Build Tools: Uses native ES modules
• No npm Dependencies: Pure JavaScript
• Offline First: Works entirely offline
• Privacy Focused: All data stored locally in IndexedDB
• Fast & Lightweight: Minimal footprint

Key Features

🎨 Modern Interface

Access all your LLMs through a clean, intuitive interface:

🌙 Dark Mode

Built-in dark mode support that respects your system preference or can be toggled manually:

📝 Rich Markdown & Syntax Highlighting

Full markdown rendering with syntax highlighting for popular programming languages:

Code blocks include:

• Copy to clipboard on hover
• Language detection
• Line numbers
• Syntax highlighting

🔍 Search History

Quickly find past conversations with built-in search:

🎯 Smart Autocomplete

Autocomplete for models and system prompts makes it easy to find what you need:

Features:

• Filters to enabled providers only
• Real-time search
• Keyboard navigation
• Recently used models

📚 System Prompt Library

Access 200+ professional system prompts for various use cases:

Categories include:

• Technical assistance
• Creative writing
• Data analysis
• Code review
• Translation
• And many more...

Customize prompts in ~/.llms/ui.json:

{
  "prompts": [
    {
      "id": "it-expert",
      "name": "Act as an IT Expert",
      "value": "I want you to act as an IT Expert..."
    }
  ]
}

⚙️ Advanced Settings

Fine-tune AI requests with advanced options:

Available parameters:

• Temperature (0-2): Control response randomness
• Max Completion Tokens: Limit response length
• Seed: For deterministic outputs
• Top P (0-1): Nucleus sampling
• Frequency Penalty (-2.0 to 2.0): Reduce repetition
• Presence Penalty (-2.0 to 2.0): Encourage new topics
• Stop Sequences: Control where generation stops
• Reasoning Effort: For reasoning models
• Top Logprobs (0-20): Token probability analysis

🎭 Reasoning Support

Specialized rendering for reasoning models with thinking processes:

Shows:

• Thinking process (collapsed by default)
• Final response
• Clear separation between reasoning and output

📊 Token Metrics

See token usage for every message and conversation:

Displayed metrics:

• Per-message token count
• Thread total tokens
• Input vs output tokens
• Total cost
• Response time

✏️ Edit & Redo

Edit previous messages or retry with different parameters:

• Edit: Modify user messages and rerun
• Redo: Regenerate AI responses
• Hover over messages to see options

💾 Export/Import

Backup and transfer your chat history:

• Export: Save all conversations to JSON
• Import: Restore from backup
• Hold ALT while clicking Export to include analytics
• Transfer between browsers or instances

🔌 Enable/Disable Providers

Manage which providers are active in real-time:

• Toggle providers on/off
• Providers are tried in order
• Automatic failover if one fails
• See which models are available per provider

Configuration

UI Configuration

Customize the UI via ~/.llms/ui.json:

{
  "prompts": [...],
  "defaultModel": "grok-4-fast",
  "theme": "auto"
}

Server Configuration

Start the server with custom options:

# Basic server
llms --serve 8000

# With verbose logging
llms --serve 8000 --verbose

# Custom root directory for UI files
llms --serve 8000 --root /path/to/ui

Storage

All data is stored in browser IndexedDB:

• Conversations: All chat threads and messages
• Activity Logs: Request history for analytics
• Settings: UI preferences
• User Profile: If using OAuth

Data is tied to the browser origin (http://localhost:PORT), so running on different ports creates separate databases.

Privacy

The UI is designed with privacy as a priority:

• ✅ No external requests (except to configured LLM providers)
• ✅ No tracking or analytics
• ✅ No ads
• ✅ No sign-ups required
• ✅ All data stored locally
• ✅ Works entirely offline
• ✅ Open source

Performance

• Fast initial load
• Instant search
• Smooth scrolling
• Efficient rendering
• Minimal memory footprint

Browser Support

Works with modern browsers supporting:

• ES Modules
• IndexedDB
• Fetch API
• CSS Grid/Flexbox

Tested on:

• Chrome/Edge (recommended)
• Firefox
• Safari

Next Steps