This step-by-step OpenClaw installation guide walks you through setting up the open-source robotic manipulation framework on Windows 11, macOS Sequoia, and Ubuntu 24.04 — from package install to your first simulated robot movement.
OpenClaw requires a 64-bit operating system (Ubuntu 22.04+, Windows 10+, or macOS 12+), Python 3.10+, CMake 3.22+, and at least 4 GB of RAM. For simulation with the Bullet physics engine, 8 GB of RAM and a discrete GPU are recommended for smooth real-time rendering.
Add the OpenClaw APT repository with: curl -fsSL https://apt.openclaw.dev/key.gpg | sudo gpg --dearmor -o /etc/apt/keyrings/openclaw.gpg && echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/openclaw.gpg] https://apt.openclaw.dev stable main" | sudo tee /etc/apt/sources.list.d/openclaw.list. Then run sudo apt update && sudo apt install openclaw.
Download the latest MSI installer from openclaw.dev/download. Run the installer as Administrator and follow the setup wizard. The installer will configure PATH variables automatically. After installation, open a new PowerShell window and run openclaw --version to verify.
Install via Homebrew: brew tap openclaw/tap && brew install openclaw. On Apple Silicon Macs, also run: echo "export OPENCLAW_ARCH=arm64" >> ~/.zshrc && source ~/.zshrc. Verify the installation with openclaw --version.
Run openclaw doctor --fix to attempt automatic remediation. If issues persist, check the specific error codes against the troubleshooting guide at openclaw.dev/docs/troubleshooting. The most common issue is a mismatch between Python virtual environment paths and the system CMake version.
Integrate OpenAI GPT-4o, Anthropic Claude 3.5 Sonnet, Google Gemini 2.0 Flash, and self-hosted Ollama LLaMA 3 with OpenClaw for natural-language robot instruction and AI-powered manipulation planning. Includes detailed per-call and monthly cost breakdowns for each AI provider.
Deploy OpenClaw on AWS EC2 and EKS, Azure Virtual Machines and AKS, and Google Cloud Compute Engine and GKE. Includes detailed cost breakdowns per cloud, GPU instance sizing for simulation, and architecture patterns for hybrid cloud-to-robot connectivity.
Deploy OpenClaw inside Docker containers for reproducible, portable robotics development. This guide covers single-container setups, multi-service docker-compose stacks, GPU passthrough for simulation, and production image hardening.