Skip to main content

A toolkit to build GUI surfing AI agents

Project description


Surfkit

A toolkit for building AI agents that use devices
Explore the docs »

View Demo · Report Bug · Request Feature


Installation

pip install surfkit

Usage

Building Agents

Initialize a new project:

surfkit new [NAME]

Build a docker container for the agent:

surfkit build

Running Agents

Create an agent:

surfkit create agent --name foo --runtime kube

List running agents:

surfkit list agents

Get details about a specific agent:

surfkit get agent --name foo

Fetch logs for a specific agent:

surfkit logs --name foo

Delete an agent:

surfkit delete agent --name foo

Managing Devices

Create a device:

surfkit create device --type desktop --provicer gce --name bar

List devices:

surfkit list devices

View device details:

surfkit view --name bar

Delete a device:

surfkit delete device --name bar

Solving Tasks

Solve a task with an existing setup:

surfkit solve --description "search for common french ducks" --agent foo --device bar

Solve a task creating the agent ad hoc:

surfkit solve --description "search for alpaca sweaters" --device bar --agent-file ./agent.yaml

Solve a task and kill the agent post-execution:

surfkit solve --description "search for the meaning of life" --device bar --agent-file ./agent.yaml --kill

List tasks:

surfkit list tasks

Publishing Agents

Login to the hub:

surfkit login

Publish the agent:

surfkit publish

List published agent types:

surfkit list types

Run a published agent:

surfkit create agent --type SurfPizza --runtime kube

Developing

Add the following function to your ~/.zshrc (or similar)

function sk() {
    local project_dir="/path/to/surfkit/repo"
    local venv_dir="$project_dir/.venv"

    local ssh_auth_sock="$SSH_AUTH_SOCK"
    local ssh_agent_pid="$SSH_AGENT_PID"

    source "$venv_dir/bin/activate"

    export SSH_AUTH_SOCK="$ssh_auth_sock"
    export SSH_AGENT_PID="$ssh_agent_pid"

    python -m surfkit.cli.main "$@"
    deactivate
}

Replacing /path/to/surfkit/repo with the absolute path to your local repo.

Then calling sk will execute the working code in your repo from any location.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

surfkit-0.1.146.tar.gz (51.0 kB view hashes)

Uploaded Source

Built Distribution

surfkit-0.1.146-py3-none-any.whl (63.8 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page