Your AI, Your Rules
- Added a bundled
llama.cppcompletion provider profile forqwen3-35b-a3b, including configurable endpoint, sampling, token, penalty, and streaming defaults - Added an Ollama Cloud category in the Models library and model selector, backed by Ollama's dedicated cloud listing
- Added custom accent selection in Appearance with violet, blue, cyan, teal, emerald, amber, rose, slate, and custom color options
- Added runtime-generated accent shade scales so custom accents can drive buttons, links, focus rings, sliders, progress bars, selected states, and glow shadows
- Reworked Tailwind theme tokens to use CSS variables for
primaryandaccent, with generated custom palettes meeting white-text contrast targets - Refined light and dark neutral palettes to reduce glare while preserving contrast across app backgrounds, panels, inputs, and message surfaces
- Persisted accent preferences through frontend state, backend preferences, import/export defaults, local rehydration, logout cleanup, and demo mode
- Added accent translation keys across all supported locales and verified locale key parity against English
- Expanded demo-mode preference APIs so Appearance, generation, embedding, system-message, and default-model settings can be exercised without a backend connection
- Standardized the Libre WebUI wordmark through a shared
Logocomponent across loading, login, setup, sidebar, and settings surfaces - Replaced fixed violet styling in persona adaptive-learning controls with active-accent tokens
- Recolored Ollama library and Cloud badges from cyan to the design-system info-blue treatment
- Reduced noisy debug logging across optional auth, chat, document search, plugin lookup, plugin deletion, TTS, image generation, and WebSocket auth paths
- Returned package version in auth system info for UI/version display
- Updated Dependabot targeting to
mainand ignored incompatible Electron and ESLint major bumps until their upstream compatibility gaps are resolved
- Fixed a critical app-wide
Too many re-renderscrash inSettingsModalby memoizing image-generation model/plugin arrays - Fixed Ollama Cloud model pulls by tagging cloud library results with
:cloudbefore install/run actions - Fixed Ollama Cloud generation failures by stripping unsupported non-positive
num_predictvalues before cloud requests - Fixed cloud model pull functionality
- Fixed auto-title generation for persona/current-model workflows by resolving the real running model before sending title prompts
- Quietly handles expired or invalid JWTs in auth and WebSocket flows without dumping routine stack traces
- Kept the lint toolchain on ESLint 9 for compatibility with the current React plugin stack
- Expanded
DESIGN.mdwith custom accent presets, generated shade-scale behavior, token usage rules, light/dark neutral guidance, and contrast requirements
- Bumped package versions to
0.10.0 - Updated Electron to
41.7.1and Electron Builder to26.15.2 - Bumped frontend/backend dependencies including React Query, i18next, KaTeX, lucide-react, React Router, Vite, pdfjs-dist, TypeScript tooling, Tailwind Merge, Zustand, Express, Multer, Better SQLite3, and related lockfile entries
- Remediated npm security advisories through dependency and lockfile updates, including
qs,tmp,ip-address,brace-expansion,ws, and related transitive packages
Privacy-first AI chat interface. Run locally with Ollama or connect to OpenAI, Anthropic, and 9+ providers. Zero telemetry. Zero tracking.
npx libre-webui Requires Node.js 18+ and Ollama for local AI
Everything You Need
A complete AI chat solution that respects your privacy
Local & Cloud AI
Run models locally with Ollama or connect to OpenAI, Anthropic, Groq, Gemini, Mistral, and more. Your choice.
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.