What is ClawdBot?

ClawdBot is an open-source personal AI assistant that runs on your computer and can actually do things, not just chat. Think of it as “Claude with hands.” It can run terminal commands, control your smart home, remember conversations from weeks ago, and proactively reach out with reminders and briefings. It was created by Peter Steinberger (founder of PSPDFKit) in late 2025 and went massively viral, getting 80,000 GitHub stars in just a few days.

The name “Clawd” is a play on words for “Claude,” the AI model that powers it. ClawdBot is built on top of Anthropic’s Claude API and adds persistent memory, computer access, and multi-platform support. You can talk to it on WhatsApp, Telegram, Discord, Slack, or iMessage, and it remembers your conversation across all of them.

What made ClawdBot go viral was the promise of a 24/7 AI assistant that could genuinely handle tasks for you. People started buying Mac minis specifically to run ClawdBot around the clock. Chinese cloud providers like Tencent Cloud and Alibaba Cloud rushed to add one-click ClawdBot deployment. It felt like everyone was talking about it overnight.

The project has gone through name changes. ClawdBot became Moltbot, which then became OpenClaw. The core idea stayed the same, but the branding evolved as the project matured.

There are some real concerns though. Users reported burning through $300+ in API costs in just two days on basic tasks. And giving an AI unrestricted access to your system raises obvious security questions. The enthusiasm is there, but so are the risks.

I haven’t used ClawdBot myself, though I have a lot of experience with Claude Code. I’ve seen ClawdBot completely take over the internet. To be honest, this kind of thing makes AI feel more like a bubble. But it’s really fun, so I’m here for it.