RobotUse
A robot agent harness for visual action selection, subagent context management, and learning from execution through persistent playbooks.
RobotUse is a robot agent harness for language-model-driven manipulation. Agents select visual targets, choose grasps, and edit poses. Subagents keep local interaction histories and return outcomes to the main agent; the backend handles geometry, motion planning, and control. A persistent playbook carries guidance from earlier execution attempts.
⚡ How to use RobotUse
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/robotuse-team-robotuseCapabilities
Do you own RobotUse?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.