Skip to main content

Worlds

Gymnasium-like environments for web worlds

Coming Soon

Worlds is a Python library that provides Gymnasium-compatible environments for training AI agents on web-based tasks. Think of it as OpenAI Gym/Gymnasium, but for simulated web applications and APIs.

Vision

  • Simulated Web Environments: Interact with web application clones (Gmail, social media, e-commerce, etc.)
  • Dual Interface: Both visual UI and programmatic API access to environment data
  • Multimodal Observations: Support for screenshots, DOM/HTML, and accessibility tree representations
  • Flexible Action Spaces: High-level semantic actions and low-level input simulation
  • Gymnasium Compatible: Full compatibility with the Gymnasium API for seamless integration with RL frameworks

Installation

pip install worlds

Quick Start

import worlds

# More coming soon!

Status

This package is currently in early development. Stay tuned for updates!

License

MIT

Release files for worlds-py 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for worlds-py 0.0.1
File Size Uploaded
worlds_py-0.0.1.tar.gz 7.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for worlds-py 0.0.1
File Interpreter ABI Platform
worlds_py-0.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 13.2 kB

Release files / worlds_py-0.0.1.tar.gz

Download URL worlds_py-0.0.1.tar.gz
Size 7.3 kB
Tags Source
SHA-256 checksum
How to use checksums
4f7d0a72e6effecafc21d608a03ee31c76327c89e27814cc6f7280a878a7e3ac
BLAKE2b-256 checksum
How to use checksums
baeaae95fd673a4c07df2b0c43b6658db2fe2d834effc8cbade50a3d77590469
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.8.12

Release files / worlds_py-0.0.1-py3-none-any.whl

Download URL worlds_py-0.0.1-py3-none-any.whl
Size 6.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8af28b383eea7224e9875ed4e34a311c9158c226fc745113963419b386e94200
BLAKE2b-256 checksum
How to use checksums
5bfad9199f5d55e8f7a5bb402b27d6c922f148a43cebb159cf7134165d84752b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.8.12

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page