Open-source, self-hosted AI assistant you message from WhatsApp, Telegram, Slack and 10+ other chat apps
OpenClaw is an MIT-licensed gateway you run on your own hardware that connects everyday chat apps — WhatsApp, Telegram, Discord, Signal, Slack, iMessage, Teams and more — to AI agents with persistent memory, browser control and extensible skills it can even write for itself. It grew out of Peter Steinberger's viral personal-assistant project and is now stewarded by the non-profit OpenClaw Foundation. The software is free; you supply the machine and the model API keys it consumes. It installs via npm on macOS, Linux and Windows, with companion apps and mobile nodes for iOS and Android.
The software is free and open source (MIT). The real cost is the LLM usage it drives — you connect your own Claude/GPT or other model credentials — plus an always-on machine to host the gateway.
Use tool ↗The strongest open alternative to hosted assistant products: your context, memory and skills stay on your machine, reachable from whatever chat app you already use. The catch is that you are the ops and security team — sandboxing, updates and model bills are entirely on you.
Watch out: Grant full system access only within the documented sandboxing options, and treat inbound messages as untrusted input — prompt injection against a self-hosted agent hits your actual machine.
Side-by-side fact sheets against the competitors our research names — pricing, platforms, API and both verdicts on one page.
No reviews yet — be the first to review OpenClaw.
Reviews are tied to your EffectHub account — one review per tool, so the rating for OpenClaw reflects real users.
No questions yet — ask the first one about OpenClaw.
Questions about OpenClaw are tied to your EffectHub account, so answers can reach you and the section stays free of spam.