Help us improve
Share bugs, ideas, or general feedback.
From AI-Toolkit
Set up, install, configure, and deploy OpenClaw (formerly ClawdBot/MoltBot) — a personal AI assistant that runs on your own devices and connects to messaging channels. Use when users ask to "set up OpenClaw," "install ClawdBot," "install MoltBot," "deploy a personal AI assistant," "configure OpenClaw on Mac," "deploy OpenClaw to VPS," "set up OpenClaw on Hostinger," "connect OpenClaw to Telegram," "configure iMessage with OpenClaw," or any variation involving OpenClaw installation, gateway configuration, channel setup, Anthropic auth, or security hardening. Also triggers on "openclaw onboard," "openclaw doctor," "openclaw security audit," troubleshooting OpenClaw deployments, OpenClaw security, OpenClaw cost control, or ClawHub skills safety.
npx claudepluginhub aznatkoiny/zai-skills --plugin AI-ToolkitHow this skill is triggered — by the user, by Claude, or both
Slash command
/AI-Toolkit:openclaw-setupThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Deploy and configure OpenClaw — the open-source personal AI assistant (145k+ GitHub stars) — safely and correctly. This skill handles the full lifecycle: installation, Anthropic model auth, channel wiring (Telegram + iMessage), security hardening, cost control, and deployment to either a local Mac mini or a Hostinger VPS.
Conducts an interactive interview to understand goals and environment, then generates a tailored OpenClaw deployment plan with milestones, commands, and configurations.
Answers OpenClaw questions on configuration, troubleshooting, setup, architecture, features, channels, gateway, automation, models, and design decisions using clawdocs and openclaw CLIs.
Performs first-time setup of a ClaudeClaw instance: installs dependencies, authenticates messaging channels, registers the main channel, and starts background services.
Share bugs, ideas, or general feedback.
Deploy and configure OpenClaw — the open-source personal AI assistant (145k+ GitHub stars) — safely and correctly. This skill handles the full lifecycle: installation, Anthropic model auth, channel wiring (Telegram + iMessage), security hardening, cost control, and deployment to either a local Mac mini or a Hostinger VPS.
OpenClaw is a self-hosted, conversation-first AI assistant built on LLMs. Originally launched as "Clawdbot" (November 2025), renamed to "Moltbot" (January 27, 2026) after Anthropic trademark concerns, then became "OpenClaw" (January 30, 2026). It runs a local Gateway (WebSocket control plane) on your machine or server and connects to messaging channels you already use — Telegram, iMessage, WhatsApp, Discord, Slack, and 50+ others. The assistant responds through those channels using models from Anthropic, OpenAI, or other providers.
Key facts:
curl -fsSL https://openclaw.ai/install.sh | bash then openclaw onboard --install-daemon~/.openclaw/openclaw.json (JSON5 format)Before ANY installation, these four steps are non-negotiable:
Set API spending limits FIRST — Go to console.anthropic.com → Settings → Limits → set a monthly cap ($30-50/month is achievable with smart routing). A misconfigured cron job or heartbeat can cost $750+/month. Do this BEFORE pasting any API key anywhere.
Version must be 2026.1.29 or later — CVE-2026-25253 (CVSS 8.8) affects all earlier versions. It enabled 1-click remote code execution through the Control UI. After installation, verify with openclaw --version.
Gateway must bind to 127.0.0.1, NEVER 0.0.0.0 — Security researcher Maor Dayan found 42,665 publicly exposed OpenClaw instances via Shodan. 93.4% had critical auth bypasses. The root cause: Docker's default port publishing binds to 0.0.0.0 on VPS instances.
DM policy must be "pairing" or "allowlist" — Never use dmPolicy: "open" unless you fully understand the risk.
See references/security-defaults.md for the complete security guide.
Use this skill when the user wants to:
openclaw doctor, openclaw security audit)Do not use this skill for:
Follow this order. Each step links to its reference file.
Before touching anything else, go to your LLM provider's console and set a monthly spending cap. See references/anthropic-auth.md for details.
| Path | Best For | Reference |
|---|---|---|
| Mac mini (local) | Personal use, always-on home server, iMessage support, safest for non-technical users | references/mac-local-setup.md |
| Hostinger VPS | 24/7 cloud availability, Telegram-focused, Docker isolation, requires active hardening | references/hostinger-vps-setup.md |
If the user wants iMessage, they must use the Mac path (iMessage requires macOS with Messages signed in).
Configure Anthropic as the primary model provider during or after onboarding.
→ Read references/anthropic-auth.md
| Channel | Platform Requirement | Reference |
|---|---|---|
| Telegram | Any (Mac or VPS) | references/telegram-channel.md |
| iMessage | macOS only | references/imessage-channel.md |
Harden the installation with safe defaults before going live.
→ Read references/security-defaults.md
openclaw --version # Must be 2026.1.29+
openclaw doctor
openclaw security audit --deep
openclaw gateway status
openclaw channels status --probe
openclaw status --all
On VPS, verify the gateway is NOT bound to 0.0.0.0:
ss -tlnp | grep 18789
# Must show 127.0.0.1:18789, NOT 0.0.0.0:18789
When running commands for the user, Claude Code should:
openclaw --version shows 2026.1.29+openclaw onboard --install-daemon and guide the user through each interactive prompt~/.openclaw/openclaw.json with safe defaultsopenclaw doctor and openclaw security audit --deepss -tlnp | grep 18789 to confirm loopback bindingFor each interactive prompt in the wizard, explain what the option means and recommend the safe choice. Non-technical users need plain-language explanations; developers can get the concise version.
openclaw onboard --non-interactive \
--mode local --auth-choice apiKey \
--anthropic-api-key "$ANTHROPIC_API_KEY" \
--gateway-port 18789 --gateway-bind loopback \
--install-daemon --daemon-runtime node --skip-skills
Minimal safe config (Anthropic + Telegram + secure defaults):
{
agent: {
model: "anthropic/claude-opus-4-5"
},
gateway: {
bind: "loopback",
port: 18789,
auth: { mode: "token", token: "<auto-generated>" }
},
channels: {
telegram: {
enabled: true,
botToken: "<from-botfather>",
dmPolicy: "pairing",
groups: { "*": { requireMention: true } }
}
},
discovery: {
mdns: { mode: "minimal" }
}
}
| Issue | Fix |
|---|---|
openclaw --version < 2026.1.29 | Update immediately: openclaw update --channel stable — critical RCE vulnerability |
node --version < 22 | Install Node 22+ via nvm, Homebrew, or system package manager |
| Gateway won't start | Check port 18789 not in use; run openclaw doctor --fix |
| Gateway bound to 0.0.0.0 | Fix Docker port binding to "127.0.0.1:18789:18789" and restart |
| Telegram 401 Unauthorized | Regenerate bot token in BotFather; update config and restart |
| "plugin not found: telegram" | Telegram is a CHANNEL, not a plugin — config goes under channels.telegram |
| Pairing code not working | openclaw pairing approve telegram <code> — codes expire after 1 hour |
| iMessage not connecting | Verify Messages signed in; consider BlueBubbles for better reliability |
| High API costs ($100+/mo) | Set spending limits; switch heartbeat to Haiku; use tiered model routing |
| Heartbeat costing $54+/month | Switch heartbeat model to Haiku with 1-hour intervals (~$0.30/month) |
| Security audit warnings | openclaw security audit --fix to auto-apply safe defaults |
| WhatsApp status=515 error | Click Update in Control UI or restart gateway |
| ClawHub skill suspicious | Do NOT install. 26% contain vulnerabilities per Cisco research |
| File | Content |
|---|---|
references/mac-local-setup.md | Complete Mac mini local deployment walkthrough |
references/hostinger-vps-setup.md | Hostinger VPS Docker deployment guide |
references/anthropic-auth.md | Anthropic auth, cost control, and smart model routing |
references/telegram-channel.md | Telegram bot creation and channel configuration |
references/imessage-channel.md | iMessage channel setup — BlueBubbles (recommended) + legacy |
references/security-defaults.md | CVE-2026-25253, safe defaults, hardening, incident response |