About Zola
Zola is an open-source chat interface for multiple AI models, designed for developers and self-hostable. It supports cloud providers such as OpenAI, Claude and Gemini as well as local models through Ollama, and accepts a user's own API key via OpenRouter.
Key features
- 01Support for OpenAI, Claude, Gemini and Ollama
- 02Bring-your-own-key access through OpenRouter
- 03Automatic detection of local Ollama models
- 04File uploads and light or dark themes
- 05Customizable system prompt and layout options
Use cases
- 01Chatting with local models through Ollama
- 02Accessing several model providers from one self-hosted interface
- 03Customizing a chat UI from open-source code
MCP support
MCP support is listed as work in progress, and the README does not describe its client capabilities.
Details
From the project READMEZola
Zola is the open-source chat interface for all your models.

Features
- Multi-model support: OpenAI, Mistral, Claude, Gemini, Ollama (local models)
- Bring your own API key (BYOK) support via OpenRouter
- File uploads
- Clean, responsive UI with light/dark themes
- Built with Tailwind CSS, shadcn/ui, and prompt-kit
- Open-source and self-hostable
- Customizable: user system prompt, multiple layout options
- Local AI with Ollama: Run models locally with automatic model detection
- Full MCP support (wip)
Quick Start
Option 1: With OpenAI (Cloud)
git clone https://github.com/ibelick/zola.git
cd zola
npm install
echo "OPENAI_API_KEY=your-key" > .env.local
npm run dev
Option 2: With Ollama (Local)
# Install and start Ollama
curl -fsSL https://ollama.ai/install.sh | sh
ollama pull llama3.2 # or any model you prefer
# Clone and run Zola
git clone https://github.com/ibelick/zola.git
cd zola
npm install
npm run dev
Zola will automatically detect your local Ollama models!
Option 3: Docker with Ollama
git clone https://github.com/ibelick/zola.git
cd zola
docker-compose -f docker-compose.ollama.yml up
To unlock features like auth, file uploads, see INSTALL.md.
Built with
- prompt-kit — AI components
- shadcn/ui — core components
- motion-primitives — animated components
- vercel ai sdk — model integration, AI features
- supabase — auth and storage
Sponsors
License
Apache License 2.0
Notes
This is a beta release. The codebase is evolving and may change.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.