Self-host OpenClaw with Levelrail
A self-hosted personal AI agent gateway that connects chat apps and tools to the model provider you choose. Recommended container limit is 2 GiB. Measured use is 0.9 to 1.3 GiB, so a Levelrail VM needs at least 4096 MiB. The gateway trusts the ingress proxy through gateway.trustedProxies, written once to openclaw.json in the data volume.
- Authoropenclaw
- LicenceMIT
- Memory2 GiB
- Archarm64
- Services1
How to self-host OpenClaw
-
Pull the images
One image is pulled on your server.
Show images
ghcr.io/openclaw/openclaw:2026.10.5
-
Create the app
One service starts in a single Compose app, with 1 named volume mount for your data, on port 18789.
-
Fill in the secrets
1 secret is generated and stored encrypted, 5 settings are preset, you do not have to fill in anything.
-
Open it
Without a domain the app gets an sslip.io address; add --domain SERVICE=HOST to use your own.
After the first start
- Open the app address, then paste the generated gateway token (OPENCLAW_GATEWAY_TOKEN in the deployment variables) to sign in.
OpenClaw requirements
- Memory
- About 2 GiB
- Architectures
- amd64 image published, arm64 image published
- Ports
- 18789
- Domain
- Optional, an sslip.io address is used without one
- Settings
- none to fill in
- License
- MIT, permissive license
- Listed. It is in the catalog but not verified. Back up the data volume before changing an image tag.
- Host ports. It publishes port 18789 on the host, so open them in the VPS firewall only if you want that.
Install Levelrail first
On a server with Levelrail running, run the command above, or open the dashboard: Apps, New app, Browse templates, then OpenClaw. New to Levelrail? Install it on a fresh VPS first.
docker pull ghcr.io/glincker/levelrail:latest Then levelrail-cli login --device. See Getting started and the OpenClaw docs page.
Deploy OpenClaw your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy OpenClaw from the CLI
levelrail-cli templates install openclaw --name my-openclaw Deploy OpenClaw with the API
curl -X POST -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
https://levelrail.example.com/api/v1/service-templates/openclaw/install \
-d '{
"name": "my-openclaw"
}' OpenClaw configuration
OpenClaw services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| openclaw-gateway | ghcr.io/openclaw/openclaw:2026.10.5 | 18789 | openclaw_data -> /home/node/.openclaw |
OpenClaw environment variables
| Variable | Service | Value |
|---|---|---|
| OPENCLAW_CONFIG_DIR | openclaw-gateway | Preset by the template |
| OPENCLAW_GATEWAY_PORT | openclaw-gateway | Preset by the template |
| OPENCLAW_GATEWAY_TOKEN | openclaw-gateway | Generated at deploy |
| OPENCLAW_STATE_DIR | openclaw-gateway | Preset by the template |
| OPENCLAW_WORKSPACE_DIR | openclaw-gateway | Preset by the template |
| TZ | openclaw-gateway | Preset by the template |
Ports and volumes
- Ports
- 18789
- Volumes
- 1 named mount: openclaw_data -> /home/node/.openclaw
OpenClaw FAQ
How much memory does OpenClaw need?
The catalog lists about 2 GiB of memory for OpenClaw.
Does OpenClaw run on arm64?
For OpenClaw, an arm64 image is published; amd64 is image published.
What licence is OpenClaw under?
OpenClaw is licensed under MIT, which is permissive, with few conditions on reuse.
Does OpenClaw need configuration before it starts?
No. The template fills in its own defaults and generates secrets at deploy time.
Which ports does OpenClaw use?
OpenClaw listens on port 18789 inside the stack.
Where does OpenClaw keep its data?
In a named volume: openclaw_data mounted at /home/node/.openclaw.
Can I deploy OpenClaw on Dokploy or Dokku?
The services and pinned images on this page can be run on any Docker host. The public Dokploy templates list has an entry with the id openclaw for this app, so check that entry as well. Dokku deploys container images with its own commands, so the pinned image ghcr.io/openclaw/openclaw:2026.10.5 is what you deploy there.