> ## Documentation Index
> Fetch the complete documentation index at: https://bedrockdynamics.studio/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Installation

> Install roz, pull a sim container, and configure your LLM provider.

This guide covers installing the roz CLI, pulling a simulation container, and configuring an LLM provider so the agent can reason about your robot.

## Prerequisites

| Requirement     | Minimum                                                                                         |
| --------------- | ----------------------------------------------------------------------------------------------- |
| **Rust**        | 1.92 or later ([rustup.rs](https://rustup.rs/))                                                 |
| **Docker**      | Docker Desktop or Docker Engine ([docker.com](https://www.docker.com/products/docker-desktop/)) |
| **LLM API key** | Anthropic, OpenAI, Google, or local Ollama                                                      |

<Note>
  Docker must be running before you start a simulation. The code editor, agent runtime, and WASM sandbox work without Docker, but you need a sim container to actually control a robot.
</Note>

## Install the CLI

Install from crates.io:

```bash theme={null}
cargo install roz-cli
```

Or clone and build from source:

```bash theme={null}
git clone https://github.com/BedrockDynamics/roz-oss.git
cd roz-oss
cargo install --path crates/roz-cli
```

Verify the installation:

```bash theme={null}
roz --version
```

## Pull a Sim Container

Each supported robot has a Docker sim container that bundles Gazebo, the robot's middleware stack, and an MCP server. Pull the one you want to use:

<Tabs>
  <Tab title="Manipulator (UR5)">
    ```bash theme={null}
    docker pull bedrockdynamics/substrate-sim:ros2-manipulator
    ```

    A 6-DOF UR5 arm in Gazebo with MoveIt2. MCP tools: `move_to_pose`, `get_joint_state`, `stop_arm`. WASM channels: 6 joint velocities.
  </Tab>

  <Tab title="Drone (PX4)">
    ```bash theme={null}
    docker pull bedrockdynamics/substrate-sim:px4-gazebo-humble
    ```

    A PX4 quadcopter in Gazebo with MAVLink. MCP tools: `takeoff`, `land`, `go_to`. WASM channels: 4 body velocities.
  </Tab>

  <Tab title="Drone (ArduPilot)">
    ```bash theme={null}
    docker pull bedrockdynamics/substrate-sim:ardupilot-gazebo
    ```

    An ArduPilot quadcopter in Gazebo. MCP tools: `arm`, `takeoff`, `go_to`. WASM channels: 4 body velocities.
  </Tab>

  <Tab title="Mobile (Nav2)">
    ```bash theme={null}
    docker pull bedrockdynamics/substrate-sim:ros2-nav2
    ```

    A differential-drive robot in Gazebo with Nav2. MCP tools: `navigate_to`, `follow_waypoints`. WASM channels: 2 twist components.
  </Tab>
</Tabs>

## Configure Your LLM Provider

The agent needs an LLM to reason about tasks and generate control code. Set the API key for your provider:

<Tabs>
  <Tab title="Anthropic (Claude)">
    ```bash theme={null}
    export ANTHROPIC_API_KEY=sk-ant-...
    ```

    Uses Claude by default. Recommended for WASM code generation — Claude produces the most reliable WAT output.
  </Tab>

  <Tab title="OpenAI (GPT-4)">
    ```bash theme={null}
    export OPENAI_API_KEY=sk-...
    ```

    Set the provider when launching:

    ```bash theme={null}
    roz --provider openai
    ```
  </Tab>

  <Tab title="Google (Gemini)">
    ```bash theme={null}
    export GOOGLE_API_KEY=...
    ```

    Set the provider when launching:

    ```bash theme={null}
    roz --provider google
    ```
  </Tab>

  <Tab title="Ollama (Local)">
    Start the Ollama server (no API key needed):

    ```bash theme={null}
    ollama serve
    ```

    Set the provider when launching:

    ```bash theme={null}
    roz --provider ollama
    ```

    <Note>
      Local models vary in their ability to generate valid WAT code. For best results with WASM controllers, use a cloud provider. Ollama works well for MCP-tool-only workflows.
    </Note>
  </Tab>
</Tabs>

## Verify Everything

Run the built-in diagnostic to check that all dependencies are configured correctly:

```bash theme={null}
roz doctor
```

This checks for:

* Rust toolchain version
* Docker availability and daemon status
* LLM provider connectivity
* Sim container images on disk

If everything passes, you are ready to start. Head to the [Quick Start](/roz/quickstart) to control your first robot.