OpenClaw 2.0 Gets Native Computer-Use via Cua Driver
- Source
- x.com
- Date
1/ OpenClaw 2.0 is out - we're excited to have worked with the @openclaw team to bring a first-class computer-use experience directly into OpenClaw. Now you can put that experience to work: launch an OpenClaw desktop fleet on Cua Cloud Fleets, with native computer use built for multi-player agent workflows:
2/ This is deeper than an external MCP connection. OpenClaw owns the agent tool, node policy, pairing, session lifecycle, and action contract. The bundled cua-computer provider connects that path to the Cua Driver SDK.
3/ The request path is: OpenClaw agent → computer → computer.act / screen.snapshot → cua-computer → Cua Driver SDK → desktop session The user-facing contract stays in OpenClaw while the desktop runtime is Cua Driver.
4/ We exercised the same path inside a Cua Cloud Fleet VM: Fleet VM → OpenClaw Gateway → OpenClaw node → cua-computer → Cua Driver SDK → Ubuntu 24.04 XFCE/X11 desktop
Context
OpenClaw 2.0 includes a computer-use integration that Cua says it built with the OpenClaw team, according to Cua's thread. Cua describes it as deeper than an external connection: OpenClaw owns the tool, node policy, pairing, session lifecycle and action contract, while a bundled provider called cua-computer connects that path to the Cua Driver SDK, which is the desktop runtime.
The request path Cua gives runs from an OpenClaw agent's computer.act or screen.snapshot calls through cua-computer and the Cua Driver SDK to a desktop session, so the user-facing contract stays in OpenClaw. Cua says it exercised the same path inside one of its Cloud Fleet VMs, with an OpenClaw Gateway and node driving an Ubuntu 24.04 XFCE desktop, and that an OpenClaw deployment can now also be launched on Cloud Fleets.
- MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Checking sign-in…
Loading comments…