Skip to content
OpenClaw Module — Now on Fluent

Deploy Your Own Always-On AI Assistant

OpenClaw is the most-starred open-source project on GitHub right now — a self-hosted AI gateway that connects your local models and Claude API to every messaging app you use. This is the complete setup guide.

248,000 GitHub stars · Dual-node setup · ~$17–47/month to run

What Does OpenClaw Actually Do?

OpenClaw is a gateway — it sits between your messaging apps and your AI models. You send a message to your Telegram bot. OpenClaw decides whether to route it to your local Ollama model (zero cost) or Claude API (complex tasks), runs it, and replies — all within seconds.

You (Telegram): "Search for the latest papers on LLM reasoning"

→ OpenClaw detects: tool call needed

→ Routes to: Claude Sonnet (web_search skill)

→ Skill runs: DuckDuckGo search + page browse

OpenClaw: "Here are the top 5 papers from the past month..."

Total time: 3.2s · Cost: $0.008

Why Self-Host?

Commercial AI assistant services charge subscription fees, log your conversations, and lock you into their model choices. OpenClaw flips the model: you pay for compute directly, your conversations stay on your hardware, and you can plug in any model — Ollama locally, Claude API for power tasks.

OpenClaw (self-hosted)Commercial services
Cost$17–47/month (usage-based)$20–100/month (subscription)
Privacy100% on your hardwareConversations logged by provider
ModelsOllama + any APIProvider's choice
ChannelsWhatsApp, Telegram, Slack, DiscordDepends on plan
CustomizationFull — skills, hooks, personasLimited
Always-onYes (VPS)Yes

What You Get

One AI, Every Messaging App

OpenClaw sits between your models and your messaging apps. One deployment covers WhatsApp, Telegram, Slack, and Discord simultaneously — with per-channel personas and access control.

Hybrid Model Routing

Route simple queries to local Ollama (zero cost) and complex agentic tasks to Claude API. Most setups run 60–80% of queries locally, cutting API costs by the same margin.

Skills & Hooks

Extend your AI with custom tools: web search, Google Calendar, file operations, and any API you can write a JavaScript function for. Hooks trigger automations on incoming events.

Always-On, Fully Private

A $7/month Hetzner VPS keeps your assistant reachable 24/7. Tailscale mesh networking means no open ports — your deployment is invisible to the public internet.

You Own Everything

Your conversations never pass through a third-party service. Your models run on your hardware. Your API keys stay in your .env file. Full control, full privacy.

Production-Grade from Day One

Docker Compose deployment, automated backups, monitoring, update procedures, fail2ban, UFW, and a monthly security checklist — built into the setup from the start.

The Full Module — 7 Lessons

From first VPS to production-hardened, security-audited setup. Lesson 1 is free.

01
What Is OpenClaw?Free

Architecture overview, cost model, and how it complements Claude Code.

Start →
02
Dual-Node Setup Guide

Hetzner VPS + WSL2 + Ollama + Docker + Tailscale — the full 60-minute walkthrough.

Pro
03
Hybrid Model Routing

Configure routing rules, complexity thresholds, and fallback chains.

Pro
04
Messaging Channel Integrations

Connect WhatsApp, Telegram, Slack, and Discord with access control and per-channel personas.

Pro
05
Skills & Hooks Development

Build custom tools and event-driven automations in TypeScript.

Pro
06
Production Operations

Monitoring, backups, cost tracking, and incident response.

Pro
07
Security Hardening

Tailscale ACLs, token rotation, Docker isolation, and the monthly security checklist.

Pro

Ready to build your own AI assistant?

Start with the free lesson — no signup required. Upgrade to Pro when you're ready for the full dual-node setup and production ops.

Part of the Fluent course