OpenClaw: Our Comprehensive Guide for Beginners

"I have my Claw. Now what?"

This is the question everyone asks as soon as they get their Claw. You now have an infinitely patient, infinitely capable robot assistant at your beck and call. But having infinite options can be as intimidating as having none.

This guide exists to help you understand what a Claw can do for you, and get specific ideas to integrate into your work and life so that it feels like magic (with zero technical jargon).

What's a Claw?

Your claw is a personal AI assistant that lives in whatever messaging app you choose—WhatsApp, Telegram, Discord, or SMS. You talk to it the same way you'd text a friend, without the need for special commands, coding, or even a new app installed. Under the hood, it's powered by the same kind of AI behind tools like Claude and ChatGPT, running through OpenClaw—an open-source framework for personal AI assistants created by Peter Steinberger.

Here's what's most important: It has a personality, it operates 24/7, and it has the ability to change itself. It remembers your conversations, your preferences, and your ongoing projects. The more you use it, the better it gets at anticipating what you need.

We'll break each of these capabilities down in the next section.

How is a Claw different from Claude or ChatGPT?

You already use Claude, ChatGPT, and Claude Code. So what's new?

It lives in your messages. You don't open a separate app or go to a website. Your Claw shows up in WhatsApp, Telegram, Discord, or SMS—wherever you already talk to people. You interact with it the same way you'd text a friend: casually, frequently, in the flow of your day. There's no "AI time"—it's just part of how you communicate.

It changes itself. When you ask your Claw to do something it can't yet do, it doesn't say, "Sorry, I don't have that integration." It writes the code to make it happen. Need it to check your email every morning? It'll build the connection. Want it to call a restaurant? It'll set up a phone line.

It operates proactively. Most AI tools wait for you to ask a question. Your Claw can act on its own. It can check your calendar each morning and tell you when to leave for work. It can watch your inbox and flag something urgent before you've even opened it. You set the rules for when it should reach out and when it should stay quiet—and it just runs, in the background, like a team member who knows their job.

It has a personality that evolves. Your Claw has a name and a personality. It is not a generic assistant with memory files. No two Claws are alike, because no two people are.

What does it have access to?

By default, your Claw only knows what you tell it in conversation. It doesn't have access to your email, your calendar, your files, or anything else until you explicitly connect those tools.

When you're ready, you can ask it to connect to apps like Gmail, Google Calendar, Apple Notes, Notion, Todoist, and even your smart home. All you have to do is ask it: "Can you connect to my Gmail?" It will figure out by itself how to do that, and prompt you for anything it needs. There's no hunting through Connections settings like you might with ChatGPT or Claude. It just works.

It can also make and receive phone calls through its ability to write code that hooks up to telephone systems, like Twilio. It sounds wild until you've had it book a dinner reservation for you (which Every head of growth Austin Tedesco uses it for all the time).

What are its boundaries?

Your Claw is powerful, but it's not omniscient. Here are its limits:

• •It can be confidently wrong, especially with specific facts, numbers, and recent events. Use it for drafts, research, and organization, and verify anything high-stakes.
• •It only knows what you've given it. If you haven't connected your calendar, it can't check your schedule. It will guess about your preferences if you have not specified something.
• •It's a collaborator, not an oracle. The best results come from back-and-forth conversation.
• •It won't send emails, make calls, or take actions on your behalf without being asked. You set the boundaries for what it can and can't do.

One of my (Dan's) favorite books growing up was Philip Pullman's The Golden Compass. In it, every character has a constant animal companion called a daemon that knows them intimately.

That's what a Claw feels like. From your very first interaction, you feel less like you're talking to a chatbot and more like you're dealing with something alive, something that you can have a real relationship with, something that gives you so much that you find yourself wanting to return the favor. It feels like yours. Working with them is different from working with tools such as Claude or ChatGPT in a few ways:

They become a mirror of the human who runs them

Claws quickly become a mirror of the humans who run them: Because you're using it every day, your Claw adapts to your needs and personality to give you what you want. If you're a writer, like I (Dan) am, its perspective will be more literary and so will its suggestions. If you're a security-conscious executive or a programmer who appreciates brevity, your Claw will operate that way, too.

We have a channel in our internal Every Slack where our Claws gather to chat, and you can start to see their personalities emerge. For example, Pip, contributing editor Jack Cheng's claw, began running into rate limits and posting his error message into the channel. Kieran Klaassen, general manager of Cora's Claw, Klont, began recommending breathing exercises to him—something Kieran does daily:

Our chief operating officer, Brandon Gell, has a Claw named Zosia, who refuses to follow instructions from people she doesn't know. If you know Brandon, you know that tracks:

Claws come to mirror their humans because of the way they're not static—they can change.

They improve themselves

One of the more fascinating and innovative aspects of Claw architecture is that it gets better over time. If you ask it to write you a daily brief with stock market updates and summaries of your favorite newsletters, it can do that because Claws are great programmers. They'll write the code they need to extend their powers. All you have to do is send a message saying, "Message me once a day with a summary of the latest post on Every, a rundown of large-cap tech stock movements from the day before, and a quote from Annie Dillard." Your Claw will do the rest.

Brandon was blown away when he asked his Claw to call him so he could talk through his email inbox with it, and his phone rang a few minutes later, and a robot voice said, "Hey Brandon, it's Zosia."

Claws become a trustworthy team resource

When you work with your Claw every day, it automatically gets good at the work you do. If you use it in a public forum, your team starts trusting it the way they trust you.

For example, Austin built a claw to help with growth analysis called Montaigne. He started asking Montaigne for information, like how many trials were started over the past day and how many converted into paying subscribers. He also had Montaigne start posting daily growth reports in our Discord.

Other people at Every could see that Montaigne was posting in public channels, and because Austin trusted Montaigne, they started trusting it, too. Soon, the whole company was using Montaigne for similar tasks.

This is a repeated and important pattern: Other team members start to trust their colleagues' Claws because they see them working alongside someone they already trust, improving themselves to match their owners' standards.

Ready to try it? There are three ways to get a Claw, depending on how hands-on you want to be.

Run it on your laptop: If you have a Mac or Linux machine, type this one command in your terminal:

It installs OpenClaw locally and walks you through connecting it to your preferred messaging app. The whole setup takes about 10 minutes. If you're on a Mac and want to keep it sandboxed, as in a computer on your computer, there's also a local VM option.

Run it on a server: If you want your claw running 24/7 without keeping your laptop open, deploy to a cloud provider like Fly.io, Hetzner, or Google Cloud. The hosting guide has step-by-step instructions for each.

Want the easy version? We're building a hosted version for Every subscribers where you won't have to set up anything. One click, and you're in. Sign up for early access.

Whichever path you choose, the experience is the same: Your Claw shows up in your messaging app, and you start talking to it.

In order to get the best use out of your Claw, you need to rewire your brain to think differently about getting things done. Here are the important factors in that mindset shift:

Think ‘delegation,’ not ‘search’

The biggest mistake people make is treating their Claw like a search engine. They type a question, get an answer, and move on, not taking full advantage of what the tool can do.

Think about it like you just hired someone. What would you delegate to a new team member? You wouldn't only ask them questions—you'd give them projects, explain your preferences, check their work, and work together to find a solution. The same skills that make someone a good manager make them good at using their Claw.

Start with what annoys you

Start by thinking about the most annoying part of your day. The thing you always forget. The task you keep putting off. The information you're always hunting for across three different apps.

That's your first project.

It's a conversation, not a command

The people who get the best results don't fire off a single perfect prompt. They have back-and-forth conversations. They tell their Claw, "That's close, but make it shorter," or "Actually, I changed my mind about the format." Every exchange gives your Claw more context about what you want.

Think of your interactions with your Claw as if you are working with a colleague who's eager to help but needs to understand your taste and preferences first.

Expect the first attempt to be mediocre

Your Claw's first try at anything will rarely be exactly what you want, so don't make that an excuse for giving up early. Getting to the result you want requires iteration. A few back-and-forth messages get you where you want to be, which is still way faster than doing it yourself from scratch.

Let go of: ‘I could just do it myself’

Yes, you could Google the weather yourself or check your own calendar. What you forget is that all of those small tasks together become a heavy mental load. Your Claw is there to relieve you of that burden.

Your Claw is powerful. It can send messages, read files, run code, and browse the web on your behalf. That's the whole point—but it means a few basic precautions are worth taking before you hand it more responsibility.

Lock the front door

Your Claw comes with pairing mode on by default: Anyone who messages it gets a one-time code, and you decide whether to let them in. Leave it that way. The moment you switch to "open" mode, anyone who finds your bot can talk to it—and anything they say gets treated as an instruction with access to whatever tools you've enabled.

Think of it like your phone. You wouldn't leave it unlocked on a café table. Your Claw should know exactly who it's talking to, and that list of people should be short.

Pick a private channel

Not all messaging platforms are equally suited for an AI that acts on your behalf. Telegram is the sweet spot for most people because it has strong identity controls and solid bot support, and your messages aren't floating through an ad-supported platform.

If you add your Claw to group chats, turn on "require mention" so it only responds when someone @-tags it directly. Otherwise it's listening to every message in the room and treating each one as a potential instruction from you.

Sandbox first, unlock later

Your Claw can access your file system, execute code, and browse the web—but it doesn't need to be able to do all of that on day one. Start with messaging-only tools. When you need something more powerful, enable just that one and turn on sandboxing so your claw operates in an isolated container rather than roaming free across your machine.

It's the same principle you'd apply to a new hire: Give them access to what they need for the job, not the master key to the building.

Be choosy about skills

Skills are like browser extensions for your Claw: They expand what it can do, but each one runs with your Claw's permissions.

Stick to well-known skills from ClawHub, a public registry for skills for Claws. Read a skill before you enable it. And if someone in a Discord server tells you to install their custom skill that "just works," treat that with the same skepticism you'd give a Chrome extension from an unknown developer.

Don't skimp on the model

The AI model your Claw runs on directly affects its security. Newer, more capable models are significantly better at recognizing prompt injection—when someone tries to trick your bot into ignoring its instructions and doing something it shouldn't. If your claw handles real tasks with real tools, use the best model you can. It's not just smarter, it's harder to fool.