niuzaisheng/ScreenAgent
616 66PythonUpdated 1 year ago
ScreenAgent: A Computer Control Agent Driven by Visual Language Large Model (IJCAI-24)
agentaillmvlm
Our verdict: worth borrowing ideas from
Implements a VLM‑driven desktop control loop (planning‑execution‑reflection) with screenshot capture and mouse/keyboard actions, a reusable pattern for his agent tooling
Filed under browser automation in our directory.