Quickstart

This quickstart guide will help you install Rover and get it running in your system. By the end of this guide, you’ll have Rover set up and be able to create your first task with an AI coding agent.

Before you begin

Ensure you have the following prerequisites installed on your machine:

• Node.js 22 or newer
• Git
• Docker or Podman
• Supported AI Agent (Claude Code, Codex, Gemini, Cursor or Qwen)

Your first steps with Rover

Installing Rover and getting it to work for you is straightforward, just follow the steps:

1. Installing Rover

1. 1

   Install Rover

   npm

   npm install -g @endorhq/rover@latest

   pnpm

   pnpm add -g @endorhq/rover@latest

2. 2

   Check that Rover is correctly installed

   rover --version

3. 3

   Congratulations!, you are a step closer to making those agents work for you

From here on you are ready to enable Rover on a project that you have on your filesystem.

2. Initializing Rover

1. 1

   Navigate to a project in which you want to enable Rover. This project needs to have git initialized, and at least one commit has to exist in its history. You can use the following commands to create a sample project:

   mkdir -p ~/rover-quickstart && cd ~/rover-quickstart && git init && \
     touch README.md && git add README.md && git commit -m 'Initial commit'

2. 2

   Init Rover

   rover init

   Rover will detect all supported installed agents in your system. You can init Rover in as many projects as you wish.

3. 3

   Now you are ready to ask Rover its first task!

3. Asking Rover its first task

1. 1

   Navigate to the project in which you enabled Rover

   cd ~/rover-quickstart

2. 2

   Ask Rover to create a fizzbuzz program

   rover task -y "Create a fizzbuzz bash program as a programming example"

3. 3

   You can now read the Common Workflows document to see what are the common ways in which you can interact with Rover, but in the meantime you can watch the task list progress.

   rover list -w

Congratulations! You have successfully installed Rover, initialized it in a project, and created your first task. From here, you can explore more advanced features and workflows to make the most out of Rover and AI coding agents.

Common Workflows

Implement a new feature Create and assign tasks to AI coding agents to implement new features

Write technical documentation Use the tech-writer workflow to generate documentation

Iterate on tasks Refine and improve task implementations through iterations

Merge changes from tasks Integrate completed tasks into your codebase