This is the clean baseline install flow. You want the CLI installed, the gateway configured in local mode, the dashboard reachable, and the model layer verified before you expand the setup.
Quick answer
Install the CLI, run onboarding, verify the gateway, open the dashboard, and confirm the model status before you customize anything else.
Command line steps
1. Install the CLI
Use the standard installer so the rest of the docs and commands line up.
curl -fsSL https://openclaw.ai/install.sh | bash2. Run onboarding
Let OpenClaw create the config and initial gateway state.
openclaw onboard3. Verify the basics
If these checks pass, you have a clean starting point.
openclaw gateway status --require-rpc
openclaw dashboard
openclaw models statusWhat to check if it still fails
- If
gateway statusfails, debug that first. Do not add channels on top of a broken service layer. - If the dashboard opens but replies fail, inspect model auth with
openclaw models status --check. - If onboarding feels wrong because you copied older config snippets, run
openclaw doctor --fixand repeat the setup flow cleanly.
Frequently asked questions
What will I learn from How to Install and Set Up OpenClaw?
Run the standard installer, finish onboarding, verify the gateway, and only then move on to channels, fallbacks, or service tweaks. The guidance is written for practical self-hosted OpenClaw environments, but commands and configuration can change between releases.
Should I back up OpenClaw before changing the configuration?
Yes. Back up the active configuration, credentials references, channel settings, and service definitions before repairs, upgrades, or model changes, then validate the gateway and important workflows after the change.
Can Milan help with OpenClaw setup or troubleshooting?
Yes. Milan provides OpenClaw setup, model and channel configuration, secure remote access, workflow automation, troubleshooting, and deployment support.