Self-host OpenClaw on a VPS
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.
levelrail-cli templates install openclaw --name my-openclawSpecification
- Status
- Listed
- Category
- AI
- Services
- openclaw-gateway
- Ports
- 18789
- Volumes
- 1
- Memory
- about 2 GiB
- arm64
- image published
- amd64
- image published
- Settings to fill in
- none
- License
- Permissive license, MIT
- Listing
- Community template
About OpenClaw
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.
What it deploys
OpenClaw runs as one service in a single Compose app, listening on port 18789, with 1 named volume mount.
| Service | Image | Tag | Ports | Volumes |
|---|---|---|---|---|
| openclaw-gateway | ghcr.io/openclaw/openclaw | 2026.10.5 | 18789 | openclaw_data -> /home/node/.openclaw |
Before you install
- CPU architecture. arm64 listed. Every image lists linux/arm64 in its registry manifest. That is a manifest fact, not proof the app runs on Arm.
- Listed. It is in the catalog. Back up the data volume before changing an image tag.
- Host ports. It publishes port 18789 directly on the host, so open them in the VPS firewall only if you want that.
Settings and environment
You do not have to fill in anything. 1 secret is generated at deploy and stored encrypted. Values are never shown here.
| Service | Variable | Value |
|---|---|---|
| openclaw-gateway | OPENCLAW_CONFIG_DIR | Preset by the template |
| openclaw-gateway | OPENCLAW_GATEWAY_PORT | Preset by the template |
| openclaw-gateway | OPENCLAW_GATEWAY_TOKEN | Generated at deploy |
| openclaw-gateway | OPENCLAW_STATE_DIR | Preset by the template |
| openclaw-gateway | OPENCLAW_WORKSPACE_DIR | Preset by the template |
| openclaw-gateway | TZ | Preset by the template |
First run
- Open the app address, then paste the generated gateway token (OPENCLAW_GATEWAY_TOKEN in the deployment variables) to sign in.
Install OpenClaw on a VPS
-
Install Levelrail on a fresh VPS
Run this as root on a Linux server (amd64 or arm64) with ports 80 and 443 reachable. The installer prints a setup link.
curl -fsSL https://levelrail.com/install.sh | sudo sh -
Sign in
Open the setup link, choose a password, then log the CLI in. The CLI install command is
curl -fsSL https://levelrail.com/install-cli.sh | shif the machine does not have it. See Getting started.levelrail-cli login --device -
Read the template
Shows the entry, including its full compose.yaml.
levelrail-cli templates get openclaw -
Install it
This template has an install form, so the CLI fills each setting from --env, a generated secret or its default.
levelrail-cli templates install openclaw --name my-openclawTo put a service behind a domain at install, add
--domain SERVICE=HOST:levelrail-cli templates install openclaw --name my-openclaw --domain openclaw-gateway=openclaw.example.com
Without a domain the app gets an sslip.io address. You can also deploy it from the dashboard: Apps, New app, Browse templates, then OpenClaw.
Docs and upstream
More in AI
- Open WebUIA self-hosted chat interface for running local large language models through Ollama.
- Open NotebookAn open source, self-hosted alternative to NotebookLM for researching with your own sources, with podcasts and chat. Add model provider keys in the app after install.
- Ollama: Qwen 2.5 7BAlibaba's Qwen 2.5 7B model, served locally through Ollama's HTTP API.
- Ollama: Phi-3 MiniMicrosoft's Phi-3 Mini (3.8B), the smallest model in this catalog, good for constrained nodes.
- Ollama: Mistral 7BMistral's 7B instruct model, served locally through Ollama's HTTP API.
- Ollama: Llama 3 8BMeta's Llama 3 8B model, served locally through Ollama's HTTP API.