Quickstart

Install DimOS, run a replay or simulation, then explore CLI and MCP. No hardware required.

In this quickstart, you will be able to replay a Unitree Go2 office navigation session with no hardware, switch to simulation or a live robot.

If you use coding agents (OpenClaw, Claude Code or similar), point them at AGENTS.md.

System requirements

Component	Minimum	Recommended
OS	Ubuntu 22.04, macOS 12.6+	Ubuntu 24.04
Python	3.12	Latest
RAM	16 GB	32 GB+
Disk	10 GB SSD	25 GB+ SSD
CPU	8-core Intel / AMD	12+ cores
GPU (optional)	NVIDIA RTX 3000+ (8 GB VRAM)	RTX 4070+ (12 GB+ VRAM)

GPU is required only for perception, VLMs, and AI features. Optional for basic robot control.

Interactive install

curl -fsSL https://raw.githubusercontent.com/dimensionalOS/dimos/main/scripts/install.sh | bash

Manual system install

If you prefer to install system dependencies yourself, follow the guide for your OS:

OS Guide	Notes
Ubuntu	Primary tested path
Nix	Flakes and dev shell
macOS	Homebrew-based; less mature than Linux

Python environment

DimOS targets Python 3.12. The examples use uv; plain python -m venv and pip work too.

uv venv --python "3.12"
source .venv/bin/activate   # Windows: .venv\Scripts\activate

Install DimOS

uv pip install 'dimos[base,unitree]'

Extras keep installs lean: base is runtime, modules, transports, and CLI; unitree adds WebRTC and skills for Go2 / G1 (real or replayed).

Replay a recorded session (no hardware)

On first run, the Rerun window may stay black briefly while roughly 75 MB of data downloads from LFS.

dimos --replay run unitree-go2

Simulation (MuJoCo)

uv pip install 'dimos[base,unitree,sim]'
dimos --simulation run unitree-go2
dimos --simulation run unitree-g1-sim   # humanoid

Real robot (example: Unitree Go2 over WebRTC)

export ROBOT_IP=<YOUR_ROBOT_IP>
dimos run unitree-go2

Do not skip the platform guide - latency, time sync, and safety habits matter: Unitree Go2.

Featured runfiles

Command	What it does
dimos --replay run unitree-go2	Quadruped navigation replay - SLAM, costmap, A-star planning
dimos --replay --replay-db go2_bigoffice run unitree-go2-memory	Quadruped temporal memory replay
dimos --simulation run unitree-go2-agentic	Quadruped agentic + MCP server in simulation
dimos --simulation run unitree-g1-sim	Humanoid in MuJoCo simulation
dimos --replay run drone-basic	Drone video + telemetry replay
dimos --replay run drone-agentic	Drone + LLM agent with flight skills (replay)
dimos run demo-camera	Webcam demo - no hardware needed
dimos run keyboard-teleop-xarm7	Keyboard teleop with mock xArm7 (dimos[manipulation] extra)
dimos --simulation run unitree-go2-agentic-ollama	Quadruped agentic with local LLM (Ollama running, ollama serve)

Blueprint reference: Blueprints.

Agent CLI and MCP

The dimos CLI runs blueprints, inspects state, talks to agents, and invokes skills via MCP.

dimos run unitree-go2-agentic --daemon   # background
dimos status
dimos log -f
dimos agent-send "explore the room"
dimos mcp list-tools
dimos mcp call relative_move --arg forward=0.5
dimos stop

Full reference: CLI.

What next?

Add an LLM agent

Natural language control and MCP-exposed skills.

Pick your platform

Hardware support matrix and bring-up guides.

Core concepts

Modules, streams, and blueprints behind every workflow.

Capabilities

Navigation, perception, spatial memory, and manipulation.