Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

Agent S: an open agentic framework that uses computers like a human

Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.

A research prototype of a human-centered web agent

Fara-7B: An Efficient Agentic Model for Computer Use

This is the official website for TuriX Computer-use-Agent

Autonomous Agents (LLMs) research papers. Updated Daily.

OpenCUA: Open Foundations for Computer-Use Agents

A Python high-performance screen capture library for Windows using Desktop Duplication API - Updated 2026

State of the Art 82% OSWorld Verified Computer Using Agent, fully open-source, safe, auditable, and production-ready.

EvoCUA: Evolving Computer Use Agent

Official implementation of "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience"

Computer Environments Elicit General Agentic Intelligence in LLMs

AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app ready.

[ICLR 2026] Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"

[NeurIPS 2025] Official repository of RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

[AAAI 2026]Release of code, datasets and model for our work TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents

DART-GUI: Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation

A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]