Getting Started with Sovereign Workflows

Get the full Sovereign Workflows stack running on your infrastructure in under 10 minutes using Docker Compose.

1Prerequisites

Docker (v24+) and Docker Compose (v2+) installed
A valid Sovereign license key (.lic file) — obtain one from your Portal dashboard
4 GB RAM available to Docker, 8 GB recommended
Port 4723 available (reverse proxy — the only port you need to access)

2Download Files

Download the Docker Compose configuration and environment template:

Or use curl:

curl -O https://portal.nemorion.com/downloads/docker-compose.yml
curl -O https://portal.nemorion.com/downloads/.env.example

init-db.sql

init-db.sql creates the Auth database on first Postgres start. Place all three files in the same directory.

3Configure Environment

Copy the example file and set the required values:

cp .env.example .env

Required Environment Variables

The alpha uses Bypass authentication — no login required. This keeps setup minimal. You only need to set three passwords:

Variable	Description	How to Generate
`POSTGRES_PASSWORD`	Database password	`openssl rand -base64 32`
`RABBITMQ_PASSWORD`	Message queue password	`openssl rand -base64 32`
`CONNECTOR_GLOBAL_SERVICE_KEY`	Executor-to-connector auth	`openssl rand -base64 32`

Everything else has sensible defaults. LLM Chat works out of the box with a Nemorion-provided API key — no configuration needed.

Place Your License File

Copy your .lic file to the same directory as docker-compose.yml:

# Default expected path (configurable via LICENSE_FILE_PATH)
cp ~/Downloads/nemorion-workflows-enterprise.lic ./license.lic

4Start the Stack

docker compose up -d

Docker will pull images from GHCR, start infrastructure services first (Postgres, RabbitMQ, Redis), then application services once health checks pass. First run takes 2-3 minutes for image pulls.

Monitor startup progress:

docker compose ps
docker compose logs -f

The executor-worker starts 2 replicas by default. Adjust with EXECUTOR_REPLICAS=4 in your .env for higher throughput.

5Verify Installation

Once all containers are running, open your browser to:

http://localhost:4723

You should see the Workflows UI. Click "New Workflow" and verify that connector actions are displayed — this confirms the connectors registered successfully.

You can also verify individual services directly:

docker compose ps          # All containers should be "healthy"
curl http://localhost:4723  # Reverse proxy → UI

RabbitMQ management UI is at http://localhost:15672 (login with your configured credentials).

6Using the Platform

Workflows UI

The visual editor is available at http://localhost:4723. From here you can:

Create and edit workflows in the visual Studio editor
Browse available connector actions in the node palette
Execute workflows and view execution results
Test LLM Chat actions (pre-configured with OpenAI — works out of the box)

MCP Server (AI Agent Access)

Connect your AI agent (Claude, GPT, etc.) to the MCP Server via the reverse proxy at http://localhost:4723/mcp/. The server exposes all workflow actions as tools that AI agents can invoke directly.

The alpha includes a Nemorion-provided OpenAI API key so LLM-powered workflows work immediately. We're using this to baseline API costs and evaluate which models work best for workflow building. Your feedback on model quality is valuable!

7Troubleshooting

Port Conflicts

If a port is already in use, change it in your .env:

# Example: move Postgres to port 5433
POSTGRES_PORT=5433

Container Won't Start

Check the logs for the specific service:

docker compose logs engine-api
docker compose logs auth-api

License Errors

If the Engine API logs show license validation failures:

Verify license.lic exists in the expected path
Ensure the license hasn't expired (check your Portal dashboard)
For air-gapped deployments, heartbeat errors are expected and safe to ignore

Full Reset

This destroys all data including databases, message queues, and configuration. Only use if you need a completely clean slate.

docker compose down -v

Next Steps

Your First Workflow — Build and run a workflow step by step
Core Concepts — Understand workflows, nodes, edges, and triggers
Studio Editor — Learn the full capabilities of the visual editor