Private AI Agent — Quick Start

2026 Edition
One Page · Zero Cloud
┌─────────────────────────────────────────────────┐
  OLLAMA ───→ OPENCLAW ───→ TELEGRAM / WHATSAPP / WEB  
  (AI brain)    (agent)           (you)          
└─────────────────────────────────────────────────┘
Step 1 — Install Ollama

Get the AI Brain

Runs AI models locally on your hardware. Nothing leaves your machine.

# Linux / macOS / WSL
curl -fsSL https://ollama.ai/install.sh | sh
Step 2 — Download a Model

Pick Your Model

Choose based on your RAM. All support tool calling.

RAMModelCommand
8 GBQwen3 4Bollama pull qwen3:4b
16 GB ★Qwen3 8Bollama pull qwen3:8b
32 GBQwen3 14Bollama pull qwen3:14b
GPU 16+Mistral Small 3.2ollama pull mistral-small3.2

Test it: ollama run qwen3:8b "What is 2+2?"

Step 3 — Install OpenClaw

Build the Agent

Gives your AI persistent memory, tools, web browsing, messaging, and automation.

# Install (Node.js 22+ required)
curl -fsSL https://openclaw.ai/install.sh | bash

Alternative: npm install -g openclaw@latest

Step 4 — Run the Setup Wizard

One Command Does It All

The wizard walks you through everything — model selection, auth, channels (Telegram, WhatsApp, Discord), and auto-start.

openclaw onboard --install-daemon
The Wizard Handles

✦ Model & auth configuration
✦ Telegram / WhatsApp / Discord setup
✦ Workspace & memory bootstrap
✦ Background service install
✦ Health check

Choose QuickStart for defaults or Advanced for full control.

Or — Use Claude Instead

No Local Hardware Needed

Don't want to run Ollama? Skip steps 1–2 and use Claude as your model. The wizard supports it — just pick Anthropic during setup.

You'll need either a Claude Pro/Max subscription or an Anthropic API key from console.anthropic.com. Claude is smarter than most local models and works instantly — you just pay per use.

The wizard also supports OpenAI, OpenRouter, and other cloud providers.

Step 5 — Chat Instantly

Talk to Your Agent

No channel setup needed for a quick test — just open the web dashboard:

openclaw dashboard

Or visit http://localhost:18789 in your browser. Start chatting immediately.

Done

Agent responds? You now have a fully private AI agent on your own hardware. No data leaves your machine.

Step 6 — Connect Your Phone

Telegram / WhatsApp / Discord

If you didn't set up a channel during the wizard, run:

# Reconfigure channels anytime
openclaw configure

# Or link WhatsApp directly
openclaw channels login

Message your bot. Wait 10–60 seconds. That's it.

Bonus — Claude Code

AI Coding Partner

Pair with Claude Code for coding tasks alongside your agent.

curl -fsSL https://claude.ai/install.sh | bash
cd your-project && claude
Useful Commands

Reference

openclaw status          # full system status
openclaw doctor          # diagnose issues
openclaw health          # health check
openclaw configure       # reconfigure anything
openclaw gateway restart # restart agent
openclaw dashboard       # open web chat
⚠️ Security — Read This

Lock It Down

Ollama has no authentication. By default it binds to localhost (safe), but if you expose it to your network or internet, anyone can use your AI, steal your models, or execute code (CVE-2024-37032). Never change OLLAMA_HOST to 0.0.0.0 unless behind a firewall.

# Run the OpenClaw security audit
openclaw security audit --deep

# Auto-fix common issues
openclaw security audit --fix
Beginner Mistakes That Get You Hacked

✗ Exposing Ollama to the internet (no auth!)
✗ Setting OpenClaw DM policy to "open" (anyone can control your agent)
✗ Skipping the gateway auth token
✗ Giving the agent shell access without sandboxing
✓ The wizard sets safe defaults — don't weaken them.

Stuck? Need help?

Join the community — get help with setup, share what you've built, and stay updated on new models and features.

Join on Telegram →

This quick start gets you running. If you want to go deeper — GPU optimization, model comparisons, building custom tools, multi-agent setups, troubleshooting — I wrote a full 12-chapter guide. PDF sent to your email instantly after purchase.