PilotDeck Docker

PilotDeck runs as two cooperating Node.js processes in the container:

• Gateway: agent runtime on PILOTDECK_GATEWAY_PORT (default 18789)
• UI Server: web frontend + REST/WebSocket adapter on SERVER_PORT (default 3001)

The Docker Compose setup persists the full PILOT_HOME directory, including generated config, auth DB, permissions, sessions/projects, memory, skills/plugins, and router stats.

Quick Start with Docker Compose

Prerequisites

• Docker v20+
• Docker Compose v2+

Option A: Configure via environment variables

Set the model provider variables in docker-compose.yml or an .env file:

PILOTDECK_MODEL=openai/gpt-4.1
PILOTDECK_API_KEY=sk-your-api-key
PILOTDECK_API_URL=https://api.openai.com/v1

Then start:

docker compose up -d --build

If /root/.pilotdeck/pilotdeck.yaml does not exist in the pilotdeck-home volume, the entrypoint generates it from the PILOTDECK_* environment variables on first start.

Option B: Configure via YAML file

Create the host config file first:

mkdir -p ~/.pilotdeck
cat > ~/.pilotdeck/pilotdeck.yaml <<'YAML'
schemaVersion: 1
agent:
  model: openai/gpt-4.1
model:
  providers:
    openai:
      protocol: openai
      url: https://api.openai.com/v1
      apiKey: sk-your-api-key
      models:
        gpt-4.1: {}
YAML

Then uncomment the config bind mount in docker-compose.yml:

volumes:
  - pilotdeck-home:/root/.pilotdeck
  - ${PILOTDECK_CONFIG:-${HOME}/.pilotdeck/pilotdeck.yaml}:/root/.pilotdeck/pilotdeck.yaml:ro

Start the service:

docker compose up -d --build

The UI is available at http://localhost:3001.

Workspace Mounts

Agents run inside the container. To let them access a host project, mount it into /workspace by uncommenting the workspace bind mount:

volumes:
  - pilotdeck-home:/root/.pilotdeck
  - ${PILOTDECK_WORKSPACE:-${PWD}}:/workspace

You can set PILOTDECK_WORKSPACE=/path/to/project before running docker compose up.

Manual Docker Build & Run

Build the image

docker build -t pilotdeck:latest .

Run with environment variables

docker run -d --name pilotdeck \
  -p 3001:3001 \
  -v pilotdeck-home:/root/.pilotdeck \
  -e PILOTDECK_MODEL=openai/gpt-4.1 \
  -e PILOTDECK_API_KEY=sk-your-api-key \
  -e PILOTDECK_API_URL=https://api.openai.com/v1 \
  pilotdeck:latest

Run with a config file

docker run -d --name pilotdeck \
  -p 3001:3001 \
  -v pilotdeck-home:/root/.pilotdeck \
  -v ~/.pilotdeck/pilotdeck.yaml:/root/.pilotdeck/pilotdeck.yaml:ro \
  pilotdeck:latest

Run with a workspace mount

docker run -d --name pilotdeck \
  -p 3001:3001 \
  -v pilotdeck-home:/root/.pilotdeck \
  -v "$PWD":/workspace \
  -e PILOTDECK_MODEL=openai/gpt-4.1 \
  -e PILOTDECK_API_KEY=sk-your-api-key \
  -e PILOTDECK_API_URL=https://api.openai.com/v1 \
  pilotdeck:latest

Run with a proxy

docker run -d --name pilotdeck \
  -p 3001:3001 \
  -v pilotdeck-home:/root/.pilotdeck \
  -e PILOTDECK_MODEL=openai/gpt-4.1 \
  -e PILOTDECK_API_KEY=sk-your-api-key \
  -e PILOTDECK_API_URL=https://api.openai.com/v1 \
  -e PILOTDECK_PROXY=http://host.docker.internal:7890 \
  pilotdeck:latest

Environment Variables

Architecture

Browser (localhost:3001) ──► UI Server (port 3001) ──► Gateway (port 18789)

Both processes are managed by concurrently inside the Docker container.

Development

npm install
npm run dev

This starts the Gateway and UI dev server with hot reload.