Guides·Guide
The open-source autonomous AI agent that runs on your own machine and actually does things, explained.
TL;DR
OpenClaw is an open-source, self-hosted AI agent that runs on your own machine and acts on your behalf across the apps you already use.
OpenClaw is a self-hosted autonomous agent: a local process you run that connects a large language model to your tools and channels, and lets it take actions, not just answer questions. It is open source, runs on your own hardware or server, and is model-agnostic, so you bring your own provider and model.
It went from release to one of the most starred projects on GitHub very fast, because it made an AI that actually does things something you can run yourself.
A chatbot answers. OpenClaw acts.
At its core, OpenClaw is a gateway. It receives a request (from a chat app or a schedule), passes context to an LLM, and the model decides which tools or skills to call to get the job done. It can browse, use connected apps, run skills, and report back on the channel you use. You give it goals; it dispatches the work and comes back with the result.
Your channels
Chat, email, a schedule
OpenClaw gateway
Receives the goal, dispatches the work
LLM
Decides which tools to call
Tools and skills
Browser, apps, APIs, files
Skills are how OpenClaw gains new abilities. Beyond built-in actions, you connect apps (email, calendars, CRMs, dev tools) so the agent can operate them. The more skills and integrations wired in, the more real work it can do without you.
Where it gets hard is scale.
One agent
Easy to babysit.
A fleet, by hand
If you only need one agent on your own box, self-hosting is the right call. The moment you need many agents online around the clock, recovering on their own, versioned and integrated, you are running infrastructure.
That is where a managed OpenClaw runtime helps: it keeps each agent alive with automatic recovery, packs many safely on shared capacity, versions their state, and ships integrations, browser automation and email and voice out of the box, so you run agents instead of operating a platform. Molted is one such managed environment for OpenClaw at scale.
Q.01
The software is open source and free to self-host. You pay for your own compute and the LLM provider you use.
Q.02
Act across your apps: send and read email, message on chat apps, browse the web, call tools and APIs, run skills, and keep state between tasks.
Q.03
Yes. One agent runs fine on a small machine. Running many reliably needs recovery, memory protection and versioning, which you either build yourself or get from a managed OpenClaw hosting platform.
Q.04
It runs on your own infrastructure, so your data and credentials stay under your control, which is a key reason teams choose a self-hosted agent.
Q.05
Yes. OpenClaw is an open-source AI agent framework, available on GitHub, that you can self-host. It is the runtime an agent runs on: it reasons, uses a browser, files and a terminal, and acts toward goals. The documentation covers setup; running it across many agents is where managed hosting comes in.
Q.06
You can, but production deployment and multi-tenant hosting of the OpenClaw agent framework mean operating recovery, isolation, integrations and density yourself. Molted runs OpenClaw as an infrastructure platform, so you get production-grade, multi-tenant OpenClaw hosting without building it.
Keep reading