PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Computer Use Python Packages

Python packages with the GitHub topic computer-use. Sorted by relevance, with stars and monthly downloads.
cuga-project
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.

335K 734 131
trycua
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).

72K 17K 1K
trycua
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).

72K 17K 1K
trycua
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).

48K 17K 1K
trycua
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).

47K 17K 1K
aadya940
orbit-cua

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

38K 5 0
CelestoAI
smolvm-core

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

13K 544 34
trycua
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).

13K 17K 1K
NaradaAI
narada-pyodide

Computer Use for Agentic Process Automation

13K 8 1
NaradaAI
narada-core

Computer Use for Agentic Process Automation

10K 8 1
NaradaAI
narada

Computer Use for Agentic Process Automation

7K 8 1
trycua
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).

6K 17K 1K
simular-ai
gui-agents

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

5K 11K 1K
AB498
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.

5K 141 29
jeomon
macos-mcp

Lightweight MCP server for computer use in MacOS

3K 42 8
onuratakan
gpt-computer-assistant

Build autonomous AI agents in Python.

3K 8K 732
reacher-z
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%.

2K 314 19
aaronlab
browsertrace

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

2K 3 23
MONTBRAIN
vadgr-computer-use

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

2K 0 0
vitalops
opendesk

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

2K 63 15
OpenAdaptAI
openadapt

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

1K 2K 238
OpenAdaptAI
openadapt-ml

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

1K 3 6
onuratakan
gcadev

Build autonomous AI agents in Python.

1K 8K 732
reacher-z
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%.

776 314 19
    • Data from PyPI, GitHub, ClickHouse, and BigQuery