Quickstart

​

Overview

These are the basic steps to getting up and running:

1. Install surfkit
2. Create an agent instance
3. Create a device
4. Launch your agent to solve a task

​

Prerequisites

• Docker
• Python >= 3.10
• MacOS or Linux
• Poetry

If you want to create a desktop using Docker, that is all you need. To create a desktop with other providers:

• Install QEMU OR Configure GCP OR Configure AWS

​

Install Surfkit

pip install surfkit

​

Run an Agent

Clone Robbie Gen 2 repository

git clone git@github.com:agentsea/robbie-g2.git && cd robbie-g2

Install dependencies

poetry install

Create a new agent

surfkit create agent -n agent01

List running agents

surfkit list agents

surfkit create agent --local-keys

surfkit logs agent <name>

surfkit logs agent <name> --follow

​

Create a Device

Now that we’ve installed our agent, we need to give it a device to use.

The fastest way to get up and running is to use Docker, but the most scalable is to create devices in GCP or AWS.

To create an Ubuntu desktop for our agent to use, select one of the following options ▼

surfkit create device --provider docker -n desktop01

surfkit create device  -n desktop01

surfkit create device --provider qemu -n desktop01

surfkit create device --provider gce -n desktop01

surfkit create device --provider ec2 -n desktop01

List running devices

surfkit list devices

​

Create a Tracker

Before solving a task, we have the choice to create a tracker, which is a task server that tracks tasks for us in a Docker container.

surfkit create tracker -n tracker01 -r docker

​

Solve a task

Use the agent to solve a task on the device

surfkit solve "Search for the most common variety of french duck" \
  --agent agent01 \
  --device desktop01 \
  --tracker tracker01

​

What’s next

Now that you have a feel for the basics, you can move on to more advanced topics, like learning about all the tools in the surfkit or creating your own agent.