open-world-agents/desktop-env
A real-time, high-frequency, real-world desktop environment that is suitable for desktop-based ML development (agents, world models, etc.)
This tool helps researchers and developers who are building AI agents that interact with desktop applications. It provides a real-time, high-fidelity capture of a user's desktop screen, keyboard, mouse, and audio. The output is recorded video and event data that can be used to train and test intelligent agents.
No commits in the last 6 months.
Use this if you need to create realistic training environments and data for AI agents that learn by observing and interacting with a standard desktop interface.
Not ideal if you are looking for a simple screen recording tool for personal use or general content creation, as its primary focus is on machine learning development and data capture.
Stars
14
Forks
—
Language
Python
License
—
Category
Last pushed
Jan 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/open-world-agents/desktop-env"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
facebookresearch/habitat-lab
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
facebookresearch/ELF
An End-To-End, Lightweight and Flexible Platform for Game Research
utra-robosoccer/soccerbot
Soccer playing robot representing Canada from University of Toronto
Project-DC/pygeneses
A PyTorch based DeepRL framework to train and study artificial species in bio-inspired environments.
cschen1205/lua-ai
Implementation of machine learning and artificial intelligence algorithms in lua with demo using game bot