Unitree Go2¶

Setup your Dog: requirements, install, connecting to your Go2, and agentic control
Simulation: try it with no hardware via replay or MuJoCo
Mapping & Navigation: live nav, premap recording, and relocalization

Available Blueprints¶

Blueprint	Description
`dimos run unitree-go2-basic`	Connection + visualization (no navigation)
`dimos run unitree-go2`	Full navigation stack
`dimos run unitree-go2-agentic`	Navigation + LLM agent + MCP tool access
`dimos run unitree-go2-agentic-ollama`	Agent with local Ollama models
`dimos run unitree-go2-spatial`	Navigation + spatial memory
`dimos run unitree-go2-detection`	Navigation + object detection
`dimos --record run unitree-go2`	Navigation + record every stream to `recordings/<run-id>/memory.db` (Recording)
`dimos run unitree-go2-memory`	Navigation + record `lidar`/`odom`/`color_image` to `.db`
`dimos --record run unitree-go2-joystick-record`	Teleop from the local keyboard window + record `joystick`, `cmd_vel` and every sensor; no mapper, viewer capped at 2 GB
`dimos run unitree-go2 --map-file=<map>`	Navigation on a saved map (`<map>.map.db`)
`dimos run unitree-go2-map`	Navigation on a map that every run extends and saves back (`map_go2`)