​
Docker (optional)

Docker is optional. Use it only if you want a containerized gateway or to validate the Docker flow.

​
Is Docker right for me?

  • Yes: you want an isolated, throwaway gateway environment or to run Pllan on a host without local installs.
  • No: you are running on your own machine and just want the fastest dev loop. Use the normal install flow instead.
  • Sandboxing note: agent sandboxing uses Docker too, but it does not require the full gateway to run in Docker. See Sandboxing.

​
Prerequisites

  • Docker Desktop (or Docker Engine) + Docker Compose v2
  • At least 2 GB RAM for image build (pnpm install may be OOM-killed on 1 GB hosts with exit 137)
  • Enough disk for images and logs
  • If running on a VPS/public host, review Security hardening for network exposure, especially Docker DOCKER-USER firewall policy.

​
Containerized Gateway

1

Build the image

From the repo root, run the setup script:
./scripts/docker/setup.sh
This builds the gateway image locally. To use a pre-built image instead:
export PLLAN_IMAGE="ghcr.io/pllan/pllan:latest"
./scripts/docker/setup.sh
Pre-built images are published at the GitHub Container Registry. Common tags: main, latest, <version> (e.g. 2026.2.26).
2

Complete onboarding

The setup script runs onboarding automatically. It will:
  • prompt for provider API keys
  • generate a gateway token and write it to .env
  • start the gateway via Docker Compose
3

Open the Control UI

Open http://127.0.0.1:18789/ in your browser and paste the token into Settings.Need the URL again?
docker compose run --rm pllan-cli dashboard --no-open
4

Configure channels (optional)

Use the CLI container to add messaging channels:
# WhatsApp (QR)
docker compose run --rm pllan-cli channels login

# Telegram
docker compose run --rm pllan-cli channels add --channel telegram --token "<token>"

# Discord
docker compose run --rm pllan-cli channels add --channel discord --token "<token>"
Docs: WhatsApp, Telegram, Discord

​
Manual flow

If you prefer to run each step yourself instead of using the setup script: 
docker build -t pllan:local -f Dockerfile .
docker compose run --rm pllan-cli onboard
docker compose up -d pllan-gateway
Run docker compose from the repo root. If you enabled PLLAN_EXTRA_MOUNTS or PLLAN_HOME_VOLUME, the setup script writes docker-compose.extra.yml; include it with -f docker-compose.yml -f docker-compose.extra.yml.

​
Environment variables

The setup script accepts these optional environment variables:
VariablePurpose
PLLAN_IMAGEUse a remote image instead of building locally
PLLAN_DOCKER_APT_PACKAGESInstall extra apt packages during build (space-separated)
PLLAN_EXTENSIONSPre-install extension deps at build time (space-separated names)
PLLAN_EXTRA_MOUNTSExtra host bind mounts (comma-separated source:target[:opts])
PLLAN_HOME_VOLUMEPersist /home/node in a named Docker volume
PLLAN_SANDBOXOpt in to sandbox bootstrap (1, true, yes, on)
PLLAN_DOCKER_SOCKETOverride Docker socket path

​
Health checks

Container probe endpoints (no auth required): 
curl -fsS http://127.0.0.1:18789/healthz   # liveness
curl -fsS http://127.0.0.1:18789/readyz     # readiness
The Docker image includes a built-in HEALTHCHECK that pings /healthz. If checks keep failing, Docker marks the container as unhealthy and orchestration systems can restart or replace it. Authenticated deep health snapshot: 
docker compose exec pllan-gateway node dist/index.js health --token "$PLLAN_GATEWAY_TOKEN"

​
LAN vs loopback

scripts/docker/setup.sh defaults PLLAN_GATEWAY_BIND=lan so host access to http://127.0.0.1:18789 works with Docker port publishing.
  • lan (default): host browser and host CLI can reach the published gateway port.
  • loopback: only processes inside the container network namespace can reach the gateway directly.
Use bind mode values in gateway.bind (lan / loopback / custom / tailnet / auto), not host aliases like 0.0.0.0 or 127.0.0.1.

​
Storage and persistence

Docker Compose bind-mounts PLLAN_CONFIG_DIR to /home/node/.pllan and PLLAN_WORKSPACE_DIR to /home/node/.pllan/workspace, so those paths survive container replacement. For full persistence details on VM deployments, see Docker VM Runtime - What persists where. Disk growth hotspots: watch media/, session JSONL files, cron/runs/*.jsonl, and rolling file logs under /tmp/pllan/.

​
Shell helpers (optional)

For easier day-to-day Docker management, install ClawDock: 
mkdir -p ~/.clawdock && curl -sL https://raw.githubusercontent.com/pllan/pllan/main/scripts/shell-helpers/clawdock-helpers.sh -o ~/.clawdock/clawdock-helpers.sh
echo 'source ~/.clawdock/clawdock-helpers.sh' >> ~/.zshrc && source ~/.zshrc
Then use clawdock-start, clawdock-stop, clawdock-dashboard, etc. Run clawdock-help for all commands. See the ClawDock Helper README. 
export PLLAN_SANDBOX=1
./scripts/docker/setup.sh
Custom socket path (e.g. rootless Docker):
export PLLAN_SANDBOX=1
export PLLAN_DOCKER_SOCKET=/run/user/1000/docker.sock
./scripts/docker/setup.sh
The script mounts docker.sock only after sandbox prerequisites pass. If sandbox setup cannot complete, the script resets agents.defaults.sandbox.mode to off.
Disable Compose pseudo-TTY allocation with -T:
docker compose run -T --rm pllan-cli gateway probe
docker compose run -T --rm pllan-cli devices list --json
pllan-cli uses network_mode: "service:pllan-gateway" so CLI commands can reach the gateway over 127.0.0.1. Treat this as a shared trust boundary. The compose config drops NET_RAW/NET_ADMIN and enables no-new-privileges on pllan-cli.
The image runs as node (uid 1000). If you see permission errors on /home/node/.pllan, make sure your host bind mounts are owned by uid 1000:
sudo chown -R 1000:1000 /path/to/pllan-config /path/to/pllan-workspace
Order your Dockerfile so dependency layers are cached. This avoids re-running pnpm install unless lockfiles change:
FROM node:24-bookworm
RUN curl -fsSL https://bun.sh/install | bash
ENV PATH="/root/.bun/bin:${PATH}"
RUN corepack enable
WORKDIR /app
COPY package.json pnpm-lock.yaml pnpm-workspace.yaml .npmrc ./
COPY ui/package.json ./ui/package.json
COPY scripts ./scripts
RUN pnpm install --frozen-lockfile
COPY . .
RUN pnpm build
RUN pnpm ui:install
RUN pnpm ui:build
ENV NODE_ENV=production
CMD ["node","dist/index.js"]
The default image is security-first and runs as non-root node. For a more full-featured container:
  1. Persist /home/node: export PLLAN_HOME_VOLUME="pllan_home"
  2. Bake system deps: export PLLAN_DOCKER_APT_PACKAGES="git curl jq"
  3. Install Playwright browsers: 
    docker compose run --rm pllan-cli \
  node /app/node_modules/playwright-core/cli.js install chromium
  4. Persist browser downloads: set PLAYWRIGHT_BROWSERS_PATH=/home/node/.cache/ms-playwright and use PLLAN_HOME_VOLUME or PLLAN_EXTRA_MOUNTS.
If you pick OpenAI Codex OAuth in the wizard, it opens a browser URL. In Docker or headless setups, copy the full redirect URL you land on and paste it back into the wizard to finish auth.
The main Docker image uses node:24-bookworm and publishes OCI base-image annotations including org.opencontainers.image.base.name, org.opencontainers.image.source, and others. See OCI image annotations.

​
Running on a VPS?

See Hetzner (Docker VPS) and Docker VM Runtime for shared VM deployment steps including binary baking, persistence, and updates.

​
Agent Sandbox

When agents.defaults.sandbox is enabled, the gateway runs agent tool execution (shell, file read/write, etc.) inside isolated Docker containers while the gateway itself stays on the host. This gives you a hard wall around untrusted or multi-tenant agent sessions without containerizing the entire gateway. Sandbox scope can be per-agent (default), per-session, or shared. Each scope gets its own workspace mounted at /workspace. You can also configure allow/deny tool policies, network isolation, resource limits, and browser containers. For full configuration, images, security notes, and multi-agent profiles, see:

​
Quick enable

{
  agents: {
    defaults: {
      sandbox: {
        mode: "non-main", // off | non-main | all
        scope: "agent", // session | agent | shared
      },
    },
  },
}
Build the default sandbox image: 
scripts/sandbox-setup.sh

​
Troubleshooting

Build the sandbox image with scripts/sandbox-setup.sh or set agents.defaults.sandbox.docker.image to your custom image. Containers are auto-created per session on demand.
Set docker.user to a UID:GID that matches your mounted workspace ownership, or chown the workspace folder.
Pllan runs commands with sh -lc (login shell), which sources /etc/profile and may reset PATH. Set docker.env.PATH to prepend your custom tool paths, or add a script under /etc/profile.d/ in your Dockerfile.
The VM needs at least 2 GB RAM. Use a larger machine class and retry.
Fetch a fresh dashboard link and approve the browser device:
docker compose run --rm pllan-cli dashboard --no-open
docker compose run --rm pllan-cli devices list
docker compose run --rm pllan-cli devices approve <requestId>
More detail: Dashboard, Devices.
Reset gateway mode and bind:
docker compose run --rm pllan-cli config set gateway.mode local
docker compose run --rm pllan-cli config set gateway.bind lan
docker compose run --rm pllan-cli devices list --url ws://127.0.0.1:18789