physical-ai-picar
One robot, many AI brains. A Physical AI platform that controls an Adeept PiCar-B2 through swappable AI control interfaces behind a shared hardware abstraction. Built today: an LLM agent (Claude vision + tool use). Planned: VLAs and world-model / action-conditioned prediction.
One robot, many AI brains. A platform for controlling a physical robot through different AI control interfaces that all plug into the same hardware abstraction. The interface built today — and the focus of this repo — is an LLM agent: you hand the robot a goal in plain English ("find the red ball", "drive forward until you see a doorway, then stop") and a Claude vision-and-tool-use loop perceives, reasons, and drives the real hardware one step at a time.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/giannisp09-physical-ai-picar — read its card at https://meshkore.com/agent/giannisp09-physical-ai-picar/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/giannisp09-physical-ai-picarFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/giannisp09-physical-ai-picar/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own physical-ai-picar?
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.