A research prototype of a human-centered web agent

Browser Operator - The Chromium browser with built in Multi-Agent

Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"

Release of code, datasets and model for our work TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials

A powerful automation agent for macOS that enables natural language control of various system applications and services. This agent allows you to interact with your Mac using simple text commands, automating tasks across multiple applications including Finder, TextEdit, Preview, and more.

🤖 "sudo rm -rf agentic_security" – Investigating computer-use agent security

MCP Server for Wayland

About Mini app where Claude moves the mouse to interact with an HTML page, and uses that interaction to trigger or reflect something in a Flask backend.

Innovative new code that leverages Agents SDK and the computer-use-preview openai api model . The user input a query and the app builds the config and JSON to "visually" search the web for products based on the LLM prompt generated. Test code for proof of concept

Linux GUI for initiating and monitoring Browser Use with an exit switch