Libre WebUI
- Added a first-class Libre Claw agent surface in the app, available from the
- Added admin-only backend proxy routes under
/api/libre-clawfor daemon - Added Libre Claw run management from WebUI: start chat or goal-mode runs, pass
- Added WebUI approval handling for Libre Claw tool calls, including
- Added Libre Claw automation controls for scheduled report/Telegram routes,
- Added Libre Claw usage and fallback visibility so admins can inspect provider
- Added backend environment configuration for Libre Claw daemon connectivity via
- Reworked the run timeline UI so assistant deltas are grouped into readable
- Added demo-safe frontend API responses for the Libre Claw page so demo mode
- Completed Libre Claw translations across all supported locales. English and
- Updated the README product overview with Libre Claw agent support, including
- Removed stale OpenClaw plugin validation hooks and the old bundled OpenClaw
- Fixed demo-mode system info so the UI reports the current built application
- Hardened artifact title sanitization by decoding basic HTML entities and
- Refreshed 17 dependencies through Dependabot, including
axios,pdfjs-dist,
- Added
docs/31-LIBRE_CLAW_INTEGRATION.mdwith setup, architecture, route - Replaced the old OpenClaw integration documentation with the Libre Claw
- The old OpenClaw integration path has been removed and replaced by Libre Claw.
A polished self-hosted AI workspace for local Ollama models, cloud providers, Libre Claw agents, personas, documents, and interactive artifacts. Private by default. Built to stay yours.
npx libre-webui Requires Node.js 18+ and Ollama for local AI
Built for Real AI Workflows
Chat, inspect, generate, and extend from one focused workspace
Control local agents without giving up your workspace.
Start chat or goal-mode runs, approve tool calls, inspect event timelines, manage schedules, and keep the agent daemon local.
Chat beside the things your model builds.
Render HTML, SVG, and React components directly in chat. Live preview with full-screen mode.
Local & Cloud AI
Run models locally with Ollama or connect to OpenAI, Anthropic, Groq, Gemini, Mistral, and more. Your choice.
Libre Claw Agents
Run durable local agents with approvals, tools, memory, automations, run timelines, and usage visibility from Libre WebUI.
Document Chat (RAG)
Upload PDFs, docs, and text files. Ask questions about your documents with semantic search and vector embeddings.
Interactive Artifacts
Render HTML, SVG, and React components directly in chat. Live preview with full-screen mode.
AES-256 Encryption
Enterprise-grade encryption for all your data. Chat history, documents, and settings are encrypted at rest.
Custom Personas
Create AI personalities with unique behaviors and system prompts. Import/export personas as JSON.
Text-to-Speech
Listen to AI responses with multiple voice options. Supports browser TTS and ElevenLabs integration.
Image Generation
Generate images with ComfyUI and Flux models. Multiple sizes, quality presets, and seamless chat integration.
Plugin Variables
Per-plugin configurable settings like temperature, endpoints, and tokens. Sensitive values are encrypted at rest.
Keyboard Shortcuts
VS Code-inspired shortcuts for power users. Navigate, toggle settings, and control everything from the keyboard.
Multi-User Support
Role-based access control with SSO support. GitHub and Hugging Face OAuth built-in.
Connect to Any Provider
One interface, unlimited possibilities
Get Started in Seconds
Choose your preferred installation method
Create Custom Plugins
Connect any OpenAI-compatible LLM with a simple JSON file
Available Plugins
Official plugins from the Libre WebUI repository. Click to view or download.
{
"id": "custom-model",
"name": "Custom Model",
"type": "completion",
"endpoint": "http://localhost:8000/v1/chat/completions",
"auth": {
"header": "Authorization",
"prefix": "Bearer ",
"key_env": "CUSTOM_MODEL_API_KEY"
},
"model_map": [
"my-fine-tuned-llama"
],
"variables": [
{
"name": "temperature",
"type": "number",
"label": "Temperature",
"default": 0.7,
"min": 0, "max": 2
}
]
}Create Your Own Plugin
Start Your LLM Server
Run any OpenAI-compatible server: llama.cpp, vLLM, Ollama, or a custom FastAPI server.
Create Plugin JSON
Define your endpoint, authentication, and available models in a simple JSON file.
Upload to Libre WebUI
Go to Settings > Providers, upload your plugin, and enter your API key.
Start Chatting
Your custom models appear in the model selector. Full privacy, full control.
Plugin Fields Reference
id Unique identifier (lowercase, hyphens allowed) name Display name shown in the UI type "completion" for chat, "tts" for text-to-speech endpoint API URL (e.g., /v1/chat/completions) auth.header Auth header name (Authorization, x-api-key) auth.prefix Key prefix ("Bearer " or empty) auth.key_env Environment variable for your API key model_map Array of available model identifiers variables Configurable settings (temperature, endpoint, etc.) Ready to Own Your AI?
Join thousands of users who value privacy and control.