OpenClaw
A self-hosted AI assistant for macOS, Windows and Linux that connects to messaging apps and works with local models, Claude and Codex.
OpenClaw is a self-hosted AI assistant that connects your own computer to the messaging services you already use. It's for people who want a personal assistant on their laptop, or teams that want to run a shared assistant on their own hardware. The project is open source under the MIT license.
The assistant runs on macOS, Windows and Linux, with Docker deployment also available. Native apps cover those desktop platforms plus iOS and Android. You can talk to it through WhatsApp, Telegram, Discord, Slack, Teams or iMessage, as well as its browser interface. Companion apps add voice, camera and screen access, plus actions on supported devices.
OpenClaw supports local models and hosted model providers. Claude and Codex are available through swappable plugins, so the assistant's model and agent backend can change while its chat connections stay in place. Tools, skills and plugins extend the tasks it can perform beyond conversation. A local Gateway manages sessions and connects the assistant to its tools and messaging channels.
State, memory and credentials stay on your hardware. Prompts still go to whichever model provider and chat platforms you choose, so self-hosting doesn't mean every interaction stays local. OpenClaw checks for updates by default; anonymous feature statistics are opt-in. Its main session runs tools directly on the host unless sandboxing is configured, and messaging channels pair unknown senders before granting access.
