Guides
How to set up OpenClaw, connect the chat apps you already use, choose where your agent should live, and keep it secure.
Start here
Getting a pod, or already have one? Start with these.
- 1What is OpenClaw? The open-source AI agent, explainedOpenClaw is free, open-source software that turns an AI model into a personal agent you message from WhatsApp or Telegram. What it does, how it works, and what it takes to run.
- 2Managed OpenClaw hosting vs self-hosting on a VPSRenting a server and doing it yourself versus paying someone to run OpenClaw for you: the work, the risks, and the costs, compared.
- 3Which AI models can a hosted OpenClaw agent use, and how do you switch?Essentially all of them: the latest from DeepSeek, Qwen, OpenAI, Anthropic, Google, and more, switched with a sentence in chat. The two levers that work, and why a switch might seem not to land.
- 4Who can see your OpenClaw agent's conversations?OpenClaw stores everything locally, but every message still passes through a chat platform and a model provider. Who can technically read what, and the dials that change it.
Getting started43 guides
Read firstHow to install OpenClaw: the three commands, and what comes afterInstalling OpenClaw takes minutes with npm. What you need first, what each command does, and the setup decisions that actually matter.- What is the OpenClaw Gateway?
- How much does OpenClaw cost? (It's free — here's what isn't)
- Running OpenClaw in Docker: images, volumes, and the port-binding trap
- Running OpenClaw on Windows: native vs WSL2
- The best model for OpenClaw: what we run, and the default trap
All 43 guides
What OpenClaw is
- Where to get OpenClaw: the official site, docs, and downloads
- What is OpenClaw? The open-source AI agent, explained
- The OpenClaw dashboard (Control UI): what it is and how to open it
- Who created OpenClaw? The story behind Clawdbot, Moltbot, and the Foundation
- Is OpenClaw legit and safe to install?
- What is Hermes? Nous Research's self-improving open-source agent
- What is Grok Bot? xAI's always-on AI teammates, explained
- What is Bot Mode for Hermes? Named bots, explained
- Do you need to know how to code to use OpenClaw?
- What is Squad? AI teammates on a dedicated OpenClaw computer, explained
Installing it
- Can you run OpenClaw on a Raspberry Pi?
- Which Node.js version does OpenClaw need?
- Build OpenClaw from source, or run the prebuilt image?
- What is a Docker container? Images, layers, and where data goes
- What does docker compose up -d actually do?
- What does npm install -g actually do?
- How to install WSL2 (and what it actually is)
- What openclaw onboard actually does, step by step
- Why your OpenClaw agent can't install anything in Docker, and what survives an image update
Models and sign-in
- Do you need an API key to use OpenClaw?
- Using your ChatGPT subscription with OpenClaw (Codex sign-in)
- Can you use your Claude subscription with OpenClaw?
- Which ChatGPT plans include Codex? All of them — here's the breakdown
- The ChatGPT setting that makes device-code sign-in work
- “Please contact your workspace admin to enable device code authentication” — the fix
- Which AI models can a hosted OpenClaw agent use, and how do you switch?
- How to change OpenClaw's thinking level (reasoning effort), for one chat or for good
Your agent's memory and identity
- What are OpenClaw skills, and how do they work?
- What is ClawHub? OpenClaw's skill registry, explained
- Hatching your OpenClaw agent: names, identity, and personality
- How OpenClaw memory works — and how to see what your agent knows
- Where does OpenClaw store its config, memory, and workspace?
- SOUL.md, IDENTITY.md, USER.md: the files that make your agent
- OpenClaw plugins vs skills: code, instructions, and the trust line
- AI agent memory, explained: what your agent remembers and where it lives
- How to start a new conversation with OpenClaw — and what it remembers
- What is OpenClaw dreaming? DREAMS.md and the 3 a.m. memory run, explained
Channels15 guides
Read firstConnecting OpenClaw to Telegram, step by stepTelegram is the easiest first channel for OpenClaw: a bot token from BotFather, one config block, no exposed ports. The full setup, including pairing.- Connecting OpenClaw to WhatsApp: how it works and what to expect
- Connecting OpenClaw to Discord, step by step
- Connecting OpenClaw to Slack (Socket Mode, two tokens, no exposed ports)
- OpenClaw and iMessage: what it really takes
- OpenClaw's Telegram pairing message, decoded (and how to approve it)
All 15 guides
Connecting a chat app
- Connecting OpenClaw to Signal with signal-cli
- OpenClaw voice calls: giving your agent a phone number
- Connecting OpenClaw to Google Chat: webhooks, service accounts, and the honest limits
- Connecting OpenClaw to Microsoft Teams, step by step
- Connecting OpenClaw to Matrix (with real end-to-end encryption)
- OpenClaw and Zalo: what works today, and which Zalo you mean
Around the connection
Running & maintaining28 guides
Read firstHow to update OpenClaw without breaking your agentUpdates are where long-running agents get hurt. The safe ritual: know your version, read the release, back up state, update deliberately, verify after.- Backing up an OpenClaw agent (and actually restoring it)
- How to stop, restart, or disable OpenClaw (without uninstalling)
- OpenClaw won't start after a config edit: crash loops, the breaker, and the clean fix
- OpenClaw cron jobs: putting your agent on a schedule
- What's new in OpenClaw 2.0, and should you upgrade yet?
All 28 guides
Updating, backing up, restarting
- How to uninstall OpenClaw completely
- What's the latest OpenClaw version? npm, GitHub, and Docker, untangled
- How to turn off OpenClaw's update banner (and why Update now does nothing)
- Keeping your agent's Ubuntu server patched, without breaking anything
When something breaks
- How to fix OpenClaw's “pairing required” (1008) scope error
- How to fix “memory search is paused” in OpenClaw
- Docker Compose .env vs env_file: two different things
- Git “detected dubious ownership”: the fix, sized right
- What openclaw doctor --fix actually does
- Your OpenClaw agent stopped answering? Check the model before the server
- “OpenClaw change was cancelled because its run ended”: the approval card, explained
- “No usable sandbox!”: why Chromium won't start for your agent in Docker on Ubuntu 24.04
- “could not read Username for 'https://github.com'” on a public repo: why a cloud server gets asked for credentials
- Why an AI agent's browser can kill a small server: Chromium tabs, the OOM killer, and swap
Making it do more
- Giving your OpenClaw agent access to a GitHub repo, the safe way
- OpenClaw hooks: run scripts when your agent starts, resets, or speaks
- Can you run multiple OpenClaw agents on one machine?
- Hermes kanban: a task board your agents work through
- What is tmux? The tool that keeps agent sessions alive
- How to change the model in OpenClaw (and why a switch might not stick)
- OpenClaw heartbeat: what your agent does every 30 minutes, and what it costs
- OpenClaw mission control: running a squad of agents on a computer of your own
Hosting choices25 guides
Read firstShould 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.- The best VPS for OpenClaw: real requirements, not guesswork
- Mac Mini vs VPS vs managed pod: where should your OpenClaw agent live?
- OpenClaw on Hetzner: the setup guide we actually operate by
- OpenClaw alternatives in 2026: other agents, and other ways to run it
- OpenClaw vs Claude Code: which agent do you actually want?
All 25 guides
Where your agent should live
- Managed OpenClaw hosting vs self-hosting on a VPS
- What is Forgejo? The community-owned Git forge, explained
- Local AI box vs cloud: should you buy your agent a computer?
- What is a VPS? A plain-language guide for agent owners
- OpenClaw 2.0 cloud sessions and nodes: do you still need a server?
- The best VM or sandbox for AI agents, by the job you're hiring it for
- What is a cloud agent? An always-on AI agent with its own computer, explained
- Why does an AI agent need its own computer?
OpenClaw against the others
- OpenClaw vs Hermes: two philosophies of open-source agent
- OpenClaw vs Claude Cowork: an agent you own, or a product you rent?
- Claude Cowork alternatives: what to pick, by what you're missing
- Grok Bot vs OpenClaw: rented AI teammates, or an agent you own?
- Grok Bot alternatives: the same always-on agents, on your terms
- OpenClaw vs Hermes vs Grok Bot: what's actually different, and where each one runs
- What AI teammates actually cost per month: Grok Bot, Squad, Hermes Cloud, and running your own
Other agents on a server
Security21 guides
Read firstWhy you should never put your OpenClaw Gateway on the public internetOpenClaw'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
- OpenClaw pairing, allowlists, and dmPolicy, explained
- OpenClaw sandboxing and exec approvals: what your agent can touch
- Is it safe to run OpenClaw on your personal computer?
- Tailscale vs Cloudflare Tunnel for reaching a private agent server
All 21 guides
Keeping your agent private
- How to run OpenClaw's security audit (and read the results)
- What is prompt injection? A plain guide for people who run AI agents
- Who can see your OpenClaw agent's conversations?
- Should OpenClaw run as root on your server?
- Does OpenRouter train on your prompts? Data policy, explained
- Is it safe to run your AI agent on a cloud machine, or should it stay on one you can unplug?
The server side
- Why your VPS logs show SSH login attempts (and when to worry)
- SSH says “REMOTE HOST IDENTIFICATION HAS CHANGED” — how to fix it safely
- What is mosh? The remote shell that survives roaming, sleep, and bad Wi-Fi
- SSH from your iPhone: the toolkit for reaching your server from anywhere
- “ssh.service is not active, cannot reload” — Ubuntu's socket-activated SSH, explained
- How to check open ports on a Linux server — from inside and outside
- How to disable SSH password login on Ubuntu — without locking yourself out
- What is SSH? A plain-language guide to Secure Shell
- What is a reverse proxy? (And when login belongs in front)
Agents on the web14 guides
Read firstWhy websites block AI agents — and what an operator can do about itBot walls can't tell your personal agent from a scraper, and there's no passlist for it. How the defenses work, what's legitimate, and what to skip.- Cloudflare Bot Fight Mode and AI agents: what it blocks, what it can't tell apart
- OpenClaw's browser: what your agent can do on the web
- What is MCP? The Model Context Protocol, explained
- What is llms.txt — and should your site have one?
- How to make your website readable by AI agents
All 14 guides
Agents and the sites they visit
- What is a HAR file? Capture, risks, and what an AI agent can do with one
- What is Kitesurf? Cloudflare's browser for AI agents
- Which websites block an AI agent running on a cloud server? We measured 83 URLs
- Tailscale exit node for a cloud agent: browse from home, run in the cloud
Your own site, and agents
- Should you block AI crawlers? Training, search, and agent bots, separated
- How to write an llms.txt for your site (with a copy-paste template)