Guides
Plain answers to the questions people actually hit when setting up OpenClaw and giving an AI agent somewhere to live — no jargon walls, no “just SSH in.”
Getting started
What is the OpenClaw Gateway?
The Gateway is the always-on process at the heart of OpenClaw — it connects your chat apps to your agent. Here's what it does, in plain language.
Do you need an API key to use OpenClaw?
Yes — OpenClaw brings the harness, you bring the model. What a model key is, where to get one, and what it costs.
Where does OpenClaw store its config, memory, and workspace?
OpenClaw keeps its config, sessions, and your agent's memory under one home directory. Where it lives, what's inside, and what to back up.
Hosting choices
Should you run OpenClaw locally or on a VPS?
Your laptop is fine for trying OpenClaw out — and wrong for living with it. How to decide where your agent should actually run.
Managed OpenClaw hosting vs self-hosting on a VPS
Renting a server and doing it yourself versus paying someone to run OpenClaw for you — an honest comparison of the work, the risks, and the costs.
Mac Mini vs VPS vs managed pod: where should your OpenClaw agent live?
The three realistic homes for an always-on OpenClaw agent, compared on price, effort, and what happens when something breaks.
Security
Is it safe to run OpenClaw on your personal computer?
OpenClaw is personal-by-default and binds to your machine only — but an autonomous agent on your laptop makes your laptop the security boundary. What that means.
Why you should never put your OpenClaw Gateway on the public internet
OpenClaw's own docs say never expose the Gateway unauthenticated. What can go wrong, and the right ways to reach your agent remotely.
What a safe OpenClaw hosting setup should include
A plain-language checklist for hosting an autonomous agent safely: private gateway, one agent per machine, pairing, pinned versions, backups, and audits.
How to run OpenClaw's security audit (and read the results)
OpenClaw ships a built-in security audit. When to run it, what --deep and --fix do, and how to make sense of the findings.