OpenClaw: The Open-Source Personal AI Assistant Taking Over GitHub
How OpenClaw became the fastest-growing open-source project on GitHub, and how to set up your own always-on AI assistant
What is OpenClaw?
OpenClaw is a free and open-source autonomous AI agent that you run on your own devices. It uses large language models to execute tasks, with messaging platforms as its primary interface. Think of it as your personal AI assistant that lives where you already communicate — WhatsApp, Telegram, Slack, Discord, Signal, iMessage, and over a dozen other platforms.
As of March 2026, OpenClaw has surpassed 250,000 stars on GitHub, overtaking React as the most-starred non-aggregator software project on the platform. It's one of the fastest-growing open-source projects in GitHub history.
The Origin Story
The project was originally published in November 2025 by Austrian developer Peter Steinberger under the name “Clawdbot.” Following trademark complaints from Anthropic, it was renamed “Moltbot” in January 2026, then quickly renamed again to “OpenClaw” after Steinberger found that “Moltbot never quite rolled off the tongue.”
The project went viral in late January 2026, partly fueled by the popularity of the companion Moltbook project. On February 14, 2026, Steinberger announced he would be joining OpenAI, with OpenClaw moving to an open-source foundation.
Key Features
Multi-Platform Messaging
OpenClaw connects to virtually every messaging platform: WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, IRC, Microsoft Teams, Matrix, LINE, Mattermost, and more. You talk to it the same way you talk to a friend — in the apps you already use.
Self-Hosted & Private
Unlike cloud-based assistants, OpenClaw runs on your own hardware. Your conversations, data, and API keys stay on your machine. This is a major differentiator for privacy-conscious users and organizations that can't send data to third-party services.
Model-Agnostic
OpenClaw works with any LLM provider — OpenAI, Anthropic, local models via Ollama, and more. You choose the brain that powers your assistant, and you can switch models without changing anything else in your setup.
Getting Started
Setting up OpenClaw takes just a few minutes. Clone the repo, configure your LLM provider and messaging platform credentials, and run the agent. The documentation covers everything from a basic single-platform setup to advanced multi-agent configurations with custom tools.
The community has also built a lightweight variant called “nanobot” for resource-constrained environments, making it possible to run a personal AI assistant on a Raspberry Pi.
Why It Matters
OpenClaw represents a shift in how people interact with AI. Instead of going to a web app or IDE, the AI comes to you — in the messaging tools you already have open all day. It's always on, always available, and completely under your control. For developers, it's also a powerful platform for building custom AI-powered automations.
Whether you want a personal research assistant, a coding helper that lives in Slack, or an always-on AI companion in WhatsApp, OpenClaw makes it remarkably easy to set up.
Tags: OpenClaw • Open Source • Personal AI