The open source personal AI assistant that runs on your own hardware and answers in your chat apps.
Technical teams that want a self-hosted assistant across every chat app
Free and open source (MIT). You pay for the model provider and the hardware you run it on.
A local Gateway connects the assistant to WhatsApp, Telegram, Slack, Teams, Discord, iMessage and more.
Hosted and local model providers are plugins, so you can change models without changing your setup.
Extend the assistant with tools, skills and plugins, many of them shared through ClawHub.
Native apps for macOS, iOS, Android, Windows and Linux add voice, camera and screen actions.
Run tools inside a sandbox and pair unknown senders before they can talk to the assistant.
Handle email, calendar and research requests from a chat thread on your phone.
Give a team one assistant in Slack or Teams that can run tasks and remember context.
Run recurring jobs that collect information and post a summary to a channel.
Close alternatives worth a look before you decide.
The self-improving open source agent from Nous Research that learns skills from experience.
A small, container-isolated alternative to OpenClaw built on the Claude Agent SDK.
An ultra-lightweight, self-hosted personal AI agent in Python with a web UI, memory and chat apps.
NVIDIA's open source stack for running OpenClaw and other agents inside secure sandboxes.
OpenClaw is an AI agent from OpenClaw Foundation. It runs as self-hosted, desktop and is offered under a open source model.
OpenClaw is offered under a open source model. Model tokens are usually billed separately, so check the live model price on this page and the vendor site for current tiers.
The alternatives section on this page lists the closest options, with live data for each. Use the head-to-head pages to compare two of them in detail.