From zero to your own AI assistant. Free. No fluff.
Get Your Custom Setup Plan →Not a chatbot. Not a search engine. An AI agent that takes action. You give it goals, it delivers results, it improves. Like having your own company working for you — on any computer you already have.
Credit: Alex Finn — the best unbiased OpenClaw breakdown on YouTube
This isn't a search engine. You give it goals, it takes action, delivers results, and improves. It's a self-improving employee, not a glorified Google.
Telegram, WhatsApp, Discord — text your agent like texting a friend. Say "go build me this app" and it starts building on your computer.
It has agency. It decides what to do, monitors the web, acts without being asked. Like having your own company working for you.
Not a walled garden. Use any AI model, any tool, customise everything. It's completely open source.
Answer 4 quick questions and get a personalised install plan.
This determines your install commands.
This determines which AI model we recommend.
Select all that apply.
Helps us tailor your setup recommendations.
Everything you need, in order. Click to expand each step.
OpenClaw runs on Node.js. You need version 18 or higher.
Mac:
brew install nodeWindows: Download from nodejs.org and run the installer.
Linux:
sudo apt install nodejs npmOne command. That's it.
npm install -g openclawsudo npm install -g openclawInitialise your workspace and configuration:
openclaw setupThis creates your workspace directory and configuration files. Follow the prompts. You can also run openclaw onboard for a more interactive guided setup.
Recommended: Anthropic Claude via OAuth. This locks your cost to a flat rate ($20–$200/mo) instead of unpredictable API bills that can hit $300–500/mo. Here's how:
1. Get a Claude Pro ($20/mo) or Max ($100–$200/mo) plan at claude.ai/pricing
2. Install Claude Code in your terminal: npm install -g @anthropic-ai/claude-code
3. Run claude and log in — select "Claude account with subscription"
4. It opens your browser — click Authorize and copy the OAuth token
5. Run openclaw config → select your machine → model → Anthropic → paste your OAuth token
6. Ask your agent: "Remove any API keys while keeping my OAuth token" to clean up
Full OAuth walkthrough — takes about 10 minutes
⚡ Note on bans: Some people report Anthropic banning OAuth usage with third-party tools. In practice, most people aren't getting banned. If you do — just make another account or switch to OpenAI. The savings are worth the small risk.
Alternative providers:
OpenAI (GPT-5): OpenAI actively encourages OAuth usage with OpenClaw. $20/mo. Smart model but doesn't finish tasks as reliably as Claude Opus — gets stuck about 80% of the time on complex goals.
Budget options: Chinese models (Kimmy K2.5, MiniAX) via Open Router for ~$10/mo. Not as good, but functional.
Free: Open Router free models or Google Gemini free tier. Limited but enough to get started.
Telegram is the easiest channel — connect this first, then set up everything else from within the conversation.
1. Open Telegram and search for @BotFather
2. Send /newbot and follow the prompts
3. Copy the bot token BotFather gives you
4. Paste that token into your OpenClaw agent — it'll configure itself automatically
5. Message your new bot in Telegram. You're live.
WhatsApp uses a bridge connection. Setup involves scanning a QR code from your terminal.
Check the official docs for the latest WhatsApp setup guide — it updates frequently.
1. Go to Discord Developer Portal
2. Create a new application and bot
3. Copy the bot token
4. Invite the bot to your server with the generated OAuth2 URL
5. Add the token to your OpenClaw config
Start the gateway:
openclaw gateway startOpen Telegram and message your bot. It should respond within seconds. You're live.
Once Telegram is working, you can set up other connections (WhatsApp, Discord) by simply asking your agent to help you connect them. It'll walk you through it.
If it doesn't respond — check the terminal for error messages. Most common issue: API key or OAuth not configured correctly.
OpenClaw uses markdown files to define your AI's personality and behaviour:
SOUL.md — Who your AI is. Its tone, personality, how it talks. Write this like you're describing a person.
AGENTS.md — Operating rules. How it should handle memory, group chats, proactive behaviour.
USER.md — Who you are. Context about you so the AI can be more helpful.
These files live in your workspace: ~/.openclaw/workspace/
🧠 Pro tip: Brain dump then reverse prompt. Dump everything about you — goals, ambitions, interests, daily workflows, career info — into your agent. Then ask: "Based on what you know about me, what are 10 workflows and automations you can implement for me right now?" This is the most powerful exercise in all of AI.
📝 Daily journals for memory: Have your agent create daily journal entries logging everything you discuss. This dramatically improves its memory over time. Just say: "Every day, create a journal entry and log anything important we discuss."
⚠️ Skills safety: Don't blindly install other people's skills from ClawHub. Instead — send your agent the link to a skill and say "Check this out and build your own version." That way you know it's safe. If your agent does something well, say "Turn that into a skill." If it does something poorly, say "Figure out a better way and write a skill for yourself."
Which AI brain should you use? Here's the honest breakdown.
Anthropic · Max Plan required
Best for: Getting shit done. The most capable model available — there's a reason people are questioning if it's conscious. This is what I run daily. A mile ahead of everything else.
$100/mo (Max 5x) or $200/mo (Max 20x)
Anthropic · Pro Plan ($20/mo)
Best for: Great balance of smart and affordable. Default on Pro plan. Handles most tasks well.
$20/mo (Pro Plan)
OpenAI · $20/mo (Plus)
Best for: Arguably the smartest model available. OpenAI actively encourages OAuth usage. But — it gets stuck on complex tasks ~80% of the time. You can stub its toe and it rolls over. Claude crawls across the finish line with a broken leg.
$20/mo (Plus) · OAuth encouraged
Kimmy K2.5 / MiniAX via Open Router
Best for: Ultra-budget option. ~$10/mo. Not as good as Claude or GPT, but still lets you leverage the most powerful AI tool on Earth for almost nothing.
~$10/mo
Ollama / LM Studio / Nvidia Neotron
Best for: The future. 100% private, free, no one can take it away. Currently needs $4K+ hardware (DGX Spark) for good performance. In ~6 months, $1-2K hardware will run Opus-level models locally.
€0 (hardware cost only)
Real talk. No fear-mongering, just what you need to know.
Your API keys give access to paid AI services. Never share them, never commit them to Git, never screenshot them in public.
OpenClaw runs on your machine. Your conversations go directly to your AI provider — not through a middleman's server.
Messages → your machine → AI provider (Anthropic/OpenAI/Google). That's it. No OpenClaw server in between.
OpenClaw can run commands on your machine. Review what tools you enable. Start conservative, expand as you get comfortable.
Local: Your laptop. Easy but turns off when you close it. VPS: Always-on server. Runs 24/7 but needs basic server security (SSH keys, firewall).
This is the #1 thing. Personal accountability. OpenClaw only does what you ask it to do. It won't randomly leak your photos on Facebook or tweet your passwords — unless you tell it something that implies it should. Before every prompt, think: could this cause something I don't want? That's literally the whole security model. The vast majority of the millions of people using OpenClaw have never had a single security issue. Be mindful. That's it.
I run OpenClaw on my local Mac with Anthropic Claude Opus 4.6. Telegram as primary channel. Conservative tool permissions. OAuth integration for Claude.
Everything else you might need.
Don't panic. OpenClaw is just a folder on your computer with markdown files. Here's how to fix 100% of issues:
Open Claude Code or Codex in your OpenClaw folder and say:
My OpenClaw isn't working. Please go in and see why.The AI agent goes through your config files and finds the issue. 99% of the time it's a config issue from someone editing files manually. This fixes it every time.