01
Imagine.
Generate and refine images in the same place you think.
Open-source creative AI workspace v0.13.0
Make whatever comes next.
Think with any model. Turn conversations into images, working artifacts, research, and agent runs inside a private workspace you own.
Paint a volcanic archipelago where fire meets turquoise water.
Open source No telemetry Local or cloud Built to be yours
01 Ideas take form
A thought can take any form.
Begin with words. End with an image, a working interface, a clearer answer, or an agent already in motion.
Created from
“Create a living poster that changes with the light.”
Output HTML / Generative
02
Build.
Turn a sentence into HTML, SVG, JSON, or code you can use.
03
Explore.
Bring documents into the conversation and follow an idea further.
04
Direct.
Run local agents with tools, memory, schedules, and approvals in your hands.
02 Your workspace
Choose the intelligence. Keep the workspace.
Use local models for private work. Reach for a cloud provider when it earns a place in the process. Libre keeps the choice visible and yours.
Explore connections Ollama OpenAI Anthropic Google Mistral Groq OpenRouter Hugging Face ComfyUI
Private when it matters.
Run Ollama on hardware you control. Your local conversations stay local.
Connected when you choose.
Add remote providers for the work that needs them, never as a hidden default.
Open by design.
Describe an OpenAI-compatible provider with JSON and make the workspace your own.
03 Begin
Start with one line.
No account to create. No workspace to rent. Run Libre WebUI and begin making.
npx libre-webui Opens at localhost:8080 Install Ollama for local models, or connect the providers you choose.
01
Instant
The shortest path from terminal to canvas.
02
Docker
A durable self-hosted workspace for your server.
03
Desktop
A native home for macOS. Windows and Linux builds are on GitHub.
04 Extend
The workspace can grow with the work.
Connect a provider, a local endpoint, or a service you built. Libre’s JSON plugin layer keeps the door open without taking over the room.
{
"id": "my-studio",
"type": "multi",
"capabilities": [
"chat", "image", "voice"
],
"endpoint":
"http://localhost:8000/v1"
} Connected localhost:8000
LIBRE / YOURS TO CREATE
What will you make first?
Open the canvas, bring the models you trust, and follow the idea.
Apache 2.0 No telemetry Self-hosted