The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visualization-of-Thought and Chain-of-Thought reasoning to elicit spatial reasoning and perception, emulates, plans and simulates synthetic HID interactions.

• UpdatedFeb 13, 2025
• Python

This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).

• UpdatedAug 16, 2025

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

• UpdatedNov 19, 2025
• Python

Mark web pages for use with vision-language models

• UpdatedMay 18, 2025
• TypeScript

🕵 Code for our EMNLP 2025 Main paper: "FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games"

• UpdatedSep 3, 2025
• Python

AI-powered assistant that controls a Windows environment through docker, allowing automated interaction with the desktop interface. Control your computer with natural language.

• UpdatedJul 24, 2025
• JavaScript

Simple, observable computer use - Remote desktop for AI agents

• UpdatedMar 22, 2025
• Rust

💻 Control AI agents to automate tasks on computers, enabling true autonomy with browser, terminal, and desktop interaction. Perfect for developers.

• UpdatedNov 29, 2025
• TypeScript

A ReAct Principles based fully autonomous Command Line Computer Using Agent

• UpdatedApr 6, 2025
• Python

A framework to enable multimodal models to operate a computer.

• UpdatedOct 14, 2025
• Python

Use an LLM agent to automate ordering food and other items from Deliveroo, Uber Eats, DoorDash, etc.

• UpdatedJan 30, 2025
• Python