Quick Start with Docker Compose
Get Actyze running locally in under 5 minutes using Docker Compose.
Prerequisites
- Docker Engine 20.10+ and Docker Compose 2.0+
- 8 GB+ RAM available for Docker
- An LLM API key (OpenAI, Anthropic, Azure OpenAI, or Google Gemini)
Steps
1. Clone the repository
git clone https://github.com/actyze/dashboard.git
cd dashboard/docker
2. Configure environment variables
cp env.example .env
Open .env in your editor and set the required values:
# Required: set at least one LLM provider
OPENAI_API_KEY=sk-...
# or
ANTHROPIC_API_KEY=sk-ant-...
# Optional: customise ports, database passwords, etc.
# See env.example for the full list of options
3. Start Actyze
docker-compose --profile local up -d
This pulls and starts all services: the React frontend, the FastAPI backend (Nexus), PostgreSQL, and the schema service.
4. Verify the services are running
docker-compose ps
All containers should show a status of Up.
Access
| Service | URL |
|---|---|
| Frontend | http://localhost:3000 |
| API | http://localhost:8000 |
| API Docs | http://localhost:8000/docs |
First Login
- Open http://localhost:3000 in your browser.
- Create an admin user on the registration screen.
- Connect your first data source (PostgreSQL, MySQL, Trino, Snowflake, MongoDB, and more).
Demo Data
TPC-H demo data is automatically loaded into the bundled PostgreSQL instance so you can start asking questions immediately — no external database required.
Try asking: "What are the top 10 customers by revenue?"
Stopping Actyze
docker-compose --profile local down
To remove all data (volumes) as well:
docker-compose --profile local down -v
Next Steps
- Configure LLM Providers to switch models or add fallback providers.
- Environment Variables for the full configuration reference.
- Features Overview to explore what Actyze can do.