Skip to main content

Spongecake is the easiest way to launch OpenAI computer use agents.

Project description

spongecake logo

Open source SDK to launch OpenAI computer use agents 🤖

[coming soon] Shows a demo of spongecake in action

(coming soonsies) Spinning up a computer use agent with sponge box

What is spongecake?

🚀 spongecake is the easiest way to launch OpenAI computer use agents.

Prerequisites

You’ll need the following to get started (click to download):

Note: The versions mentioned above are tested references. Other versions may work, but haven’t been fully validated.

Quick Start

Install the spongecake package using pip:

pip install spongecake

Clone the repo and run test.py...

cd spongecake/test
python3 test.py

Done! Edit the script in test.py to test out sponge bob

Usage Details

[coming soon]

How it works

[coming soon]

Appendix

Contributing

Feel free to open issues for any feature requests or if you encounter any bugs! We love and appreciate contributions of all forms.

Pull Request Guidelines

  1. Fork the repo and create a new branch from main.
  2. Commit changes with clear and descriptive messages.
  3. Include tests, if possible. If adding a feature or fixing a bug, please include or update the relevant tests.
  4. Open a Pull Request with a clear title and description explaining your work.

Roadmap

[coming soon]

Team

Made with ❤️ in San Francisco

Backend set-up

  • Set-up .env in the backend folder with OpenAI Key and Port

SDK set-up

  • cd sdk
  • (in spongecake) pip3 install --upgrade pip setuptools wheel build
  • (in spongecake) pip install --upgrade openai # Make sure you get the latest responses API
  • (in spongecake) python3.11 -m build
  • (in spongecake) pip3 install dist/spongecake-0.1.2-py3-none-any.whl
  • (in root) pip3 install -e spongecake/
  • pip3 install dotenv

Testing the app

  • python3 test.py

Building and running the docker container

  • cd sdk/docker
  • docker build -t local-lxde-vm
  • docker run -d -p 5900:5900 --name myvm local-lxde-vm
  • docker exec -it myvm bash

Connecting to virtual desktop

  • Open TigerVNC viewer
  • Connect to localhost:5900

Project details


Download files

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

Source Distribution

spongecake-0.1.5.tar.gz (17.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

spongecake-0.1.5-py3-none-any.whl (16.8 kB view details)

Uploaded Python 3

File details

Details for the file spongecake-0.1.5.tar.gz.

File metadata

  • Download URL: spongecake-0.1.5.tar.gz
  • Upload date:
  • Size: 17.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.11

File hashes

Hashes for spongecake-0.1.5.tar.gz
Algorithm Hash digest
SHA256 f30563158c5cca13e3257668f5bd527aa0878e62b122db2647b8fb73ba06cee7
MD5 041b3750eda5b989231d3da4ac9199f8
BLAKE2b-256 440a93ba6bde2ce3e17949232473f0e9ffc7294b35d985ab63e3175f84411457

See more details on using hashes here.

File details

Details for the file spongecake-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: spongecake-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 16.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.11

File hashes

Hashes for spongecake-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 43a7e4eacef581cccc1dc10ea7528ad9da049582487efc0c8149ff77b67c6de8
MD5 551a99ddacd1a1d41006b2be903d94fa
BLAKE2b-256 a691fc4d100670ec822975f21ddcb03447ff1b15de55e55202a1255c6a986167

See more details on using hashes here.

Supported by

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