Computer Use Python Packages

cuga

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

cua-sandbox

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).

cua-auto

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).

cua

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).

cua-cli

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).

orbit-cua

Building Blocks to automate desktop workflows end-to-end using AI

smolvm-core

Open-source AI sandbox infrastructure for code execution, browser use, and AI agents.

cua-computer-server

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).

narada-pyodide

Computer Use for Agentic Process Automation

narada-core

Computer Use for Agentic Process Automation

narada

Computer Use for Agentic Process Automation

cua-som

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).

gui-agents

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

computer-control-mcp

MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. Similar to 'computer-use' by Anthropic. With Zero External Dependencies.

macos-mcp

Lightweight MCP server for computer use in MacOS

gpt-computer-assistant

Build autonomous AI agents in Python.

clawbench-eval

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

browsertrace

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

vadgr-computer-use

MCP server for desktop automation. Accessibility-first (UIA/AT-SPI/AX) with vision fallback. Local, on-device, CPU-friendly.

opendesk

Control 1 or more machines using computer use tools that integrates with your agents

openadapt

GUI automation with ML - record, train, deploy, evaluate

openadapt-ml

OpenAdapt’s open-source ML toolkit for training and evaluating general multimodal GUI-action models.

gcadev

Build autonomous AI agents in Python.

clawbenchmark

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.