What is OpenClaw?

OpenClaw is a personal AI assistant that runs on your computer 24/7 and can do things like run terminal commands, control your smart home, and remember conversations across all your messaging apps. It’s the current name of the project that was originally called ClawdBot, then briefly Moltbot. It was created by Peter Steinberger in late 2025 and went massively viral.

The project lives at openclaw.ai and is designed to be “Claude with hands.” Unlike AI chatbots that just talk, OpenClaw has full computer access. It can execute commands, read files, control devices, and proactively reach out to you with reminders and briefings. You install it on your own hardware (people love using Mac minis for this) and it runs continuously.

What makes OpenClaw different is the persistent memory and multi-platform support. You can talk to it on WhatsApp, Telegram, Discord, Slack, or iMessage, and it remembers your entire conversation history across all of them. It’s not just a stateless chatbot. It knows who you are and what you’ve been working on.

The project is fully open source and built on Anthropic’s Claude API. You bring your own API key and run it on your own infrastructure. This gives you control over your data and costs, but it also means you’re responsible for security. Giving an AI unrestricted system access is powerful but risky.

OpenClaw is part of a broader trend toward agentic personal assistants that can actually take actions on your behalf, not just answer questions. It’s exciting technology, but users have reported burning through hundreds of dollars in API costs very quickly, so you need to be careful.