xlang-ai/OSWorld-G
[NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis
This project helps AI developers who are building agents that interact with computers by generating precise UI interaction data. It takes raw screenshots or UI element descriptions and outputs annotated data showing where an AI agent should click, along with visual feedback. The primary users are AI researchers and developers focused on creating or evaluating autonomous computer-use agents.
157 stars.
Use this if you are developing or benchmarking AI models that need to accurately understand and interact with graphical user interfaces.
Not ideal if you are looking for an off-the-shelf AI agent to perform tasks or if you are not involved in AI model development or evaluation.
Stars
157
Forks
6
Language
TypeScript
License
—
Category
Last pushed
Nov 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/xlang-ai/OSWorld-G"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Majid-Mollaeefar/auto-sec-gpt
AutoSecGPT is an AI-power tool that supports security teams to model threats associated with...
fx2y/LinguaFlow
LinguaFlow - A customizable and conversable system for next-generation large language model...
AnushkaAn/Research_tool
An AI-powered financial research tool that extracts structured insights, sentiment, and...