The wild rise of OpenClaw...

One of the most exciting AI apps for developers in 2026 is Claude. No, not that Claude, but Claudebot, a free and open- source project that's not just another lame chatbot, but a tool that takes action in the real world 24 hours a day, 7 days per week without smoke breaks. And it does this while remembering everything and will hit you up on Telegram or WhatsApp as it automates your entire life. Over the last few weeks, everybody's been going crazy over it. It's racked up over 65,000 GitHub stars in record time and caused Mac Mini sales to go through the roof, selling out everywhere. In today's video, we'll take a hands-on look at everything it can do. But its popularity has already created some problems. Earlier this week, Anthropic, a company that believes open- source AI is too dangerous for the common man, woke up and chose violence. Claudebot sounded too similar to their beloved Claude, so they threatened to break the developers knees with a lead pipe if they don't change the name. So now Claudebot is officially called Maltbot. Actually, no. Wait a minute. Maltbot. That name sucks. Today, they changed the name once again to its final form, OpenClaw. The same dangerous AI assistant with a new lobster identity. It is January 30th, 2026. And you're watching the code report. OpenClaw was created by Peter Steinberger, the founder of the developer tools company PSDFKit, aka Nutrient. But just look at this dude's unhinged GitHub profile. It's less of a resume and more of a heat map of pure uninterrupted software obsession. What's crazy is that this guy retired and then came back for an encore by giving us Moltbot for free, a tool written in Typescript that wraps Claude and GPT5 to stay alive 24/7. It can manage your calendar, clean up your email, run scripts, find out how much money you're losing in the stock market and deploy broken code with absolute confidence. And best of all, it can do all of this from your own tiny self-hosted VPS, a Raspberry Pi, or even a Mac Mini if you really want to overdo it. There's no reason to pay another random startup $29 per month for the privilege. But to understand its full power, let's put it to work right now. The first step is to install it, which can be done with a single command on any system, although Linux would be the preferred route. Once installed, you'll have access to the clawbot or moltbot command or the open claw command if you live in the present. And the first thing you'll want to do is go through onboarding. It is going to request that you read the security doc about all the risks involved, but I like to live dangerously. So, let's move right on to the next step by hooking up an AI model provider. You can use anything you want here, but I'm going to go ahead and drop in my Anthropic API key. The Anthropic API does cost money, but you could easily use a free open- source model here as well. Now that that's done, the second major component is hooking up some kind of messenger app like Telegram, Slack, WhatsApp, Discord, etc. I'm going to go with Telegram, which is really easy to set up. Just open up your Telegram Messenger and start a chat with the bot father. It'll have you select a name for your bot and then eventually give you an access token, which is like a password that you want to keep safe. Go ahead and give the token to Moltbot. Then the next thing it'll ask you for is to configure some skills. It has a bunch of built-in skills or you can bring your own. And there's even a thing called MoltHub with a bunch of other pre-built skills depending on what you want this thing to do. And then finally, it'll ask you about hooks. Hooks allow you to tap into different life cycle events that happen as this tool runs, which is really useful if you want it to keep memories about things that happen in previous sessions or trigger follow-up automations when something important happens. That takes care of the initial setup, which then brings up this gateway dashboard where you can manage everything. It has an interface for basic chat along with tons of config settings to customize basically everything. That's cool and all, but our goal is to use Mulbot through Telegram. And to do that, we need to go into Telegram and send a message to the bot we created with the bot father earlier. You'll notice initially it says access not configured. And we'll respond with this pairing code. What we have to do is take that pairing code, go into the terminal, and run this command. And now we're good to go. Now we can start sending messages and it will respond with Anthropics Claude as the backend AI model. And now we can start refining its personality by simply chatting with it. I'll go ahead and name it assistant to Jeff and tell it to behave like a casual gremlin with the fire emoji. But what's really awesome is that we can now start building automations directly in the chat. Like maybe I want to check and see how my investment in Microsoft is doing. We can ask Moltbot through Telegram and it turns out it's not doing so well. But it's not just going to pull this data once. We now have an automation set up in the background to keep track of this stock. And when it moves significantly, we'll get a message on Telegram. So now there's no need in my life to go check this stock manually. But unfortunately, because I lost so much money in Microsoft, I now need to get a real job. So I might go ahead and install this skill that will automatically generate interview questions for software engineers. But that's just the tip of the iceberg of what's possible here. It's an amazing tool you'll definitely want to try out. Kind of like Tracer, the sponsor of today's video. The Tracer is an agent orchestration layer that makes your coding agents a lot better at building real world software. You start by telling it what you want to build and Tracer's new epic mode will ask you follow-up questions to create a series of specs and tickets. It just like real engineering teams when they plan an epic. Then it passes all of that context to your favorite coding agent and tracks the progress of each ticket in your sidebar. The tracer uses a smart orchestration system called Bart Simpson that tracks what's actually happening under the hood and corrects agents the moment they drift. instead of just blindly spamming more loops. If you want to get more out of your coding agents in 2026, try out Tracer's new epic mode for free with the link below. This has been the Code Report. Thanks for watching and I will see you in the next one.