niuzaisheng/ScreenAgent

ScreenAgent: A Computer Control Agent Driven by Visual Language Large Model (IJCAI-24)

43
/ 100
Emerging

It functions by observing screenshots and outputting mouse/keyboard operations, following a "planning-execution-reflection" control loop to complete multi-step tasks. The project integrates with VNC servers for desktop control and offers inferencers for various VLMs like GPT-4V and LLaVA-1.5, or supports custom API interfaces for model interaction. A corresponding dataset, ScreenAgent dataset, facilitates training for diverse computer tasks.

579 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

579

Forks

62

Language

Python

License

Last pushed

Nov 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/niuzaisheng/ScreenAgent"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.