Computer Use Agent Python Packages

cua-driver

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

dxcam

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

cua-bench

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

cua-train

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

cua-auto

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

xa11y

Cross platform desktop accessibility library for driving native desktop apps on macOS, Windows, and Linux for end-to-end tests, computer-use agents, and assistive tools.

cua-sandbox

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

cua

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

cua-computer-server

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

cua-cli

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

cua-som

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

ailoy-py

AI agent builder with a VM at its heart. Every agent gets its own microVM sandbox to install software, run code and use the GPU in. Python, Node.js and Rust.

dsh-cua

Windows computer-use MCP server for dsh (DeepSeek Harness) — client-neutral, works with any stdio MCP client. Accessibility-first element actions, skyshot text trees, guarded raw input, and a cross-session arbiter that yields to the human.

gui-agents

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

llm-in-sandbox

Computer Environments Elicit General Agentic Intelligence in LLMs

magentic-ui

MagenticLite is an experimental agent that works across the browser and local file system

wayland-mcp

MCP Server for Wayland

tarsier-ai

Semantic UI automation and lightweight accessibility snapshots for LLM agents to interact with Web and Desktop applications.

strands-xa11y

Cross platform desktop accessibility library for driving native desktop apps on macOS, Windows, and Linux for end-to-end tests, computer-use agents, and assistive tools.

pytest-xa11y

Cross platform desktop accessibility library for driving native desktop apps on macOS, Windows, and Linux for end-to-end tests, computer-use agents, and assistive tools.

cua-cloud

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

raya-agent

let LLMs control your desktop for tasks