cua-computer
Computer-Use Interface (CUI) framework powering Cua
Decision gist · record as of 2026-08-14
Yes, if you need to automate desktop interaction on macOS or Linux and are comfortable with the unclear license status. The package is actively maintained, has low install friction, carries no known vulnerabilities, and offers a unified interface to a complex problem. Verify the license terms and system requirements before committing to production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.12,<3.14.
- Designed for local macOS or Linux environments; Windows support status unclear.
- Low install friction with a pure-Python wheel distribution.
License · maintenance · safety
(unclear) — License treatment is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms before using in proprietary or restricted-license contexts.
last release 2026-06-18 (57 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 112,018 downloads/mo, #12,384 on PyPI
Alternatives
Verify before relying
pip install cua-computer
from cua_computer import Computer
computer = Computer()
# Use computer object to interact with desktop environment- Whether the package requires specific system permissions or sandboxing setup on macOS or Linux beyond standard Python installation
- Performance characteristics and latency when controlling GUI elements across network or local connections
- Whether cua-core is a first-party dependency and what its maintenance and licensing status are
What it is and what it does
Cua Computer is a framework for building automation and control systems that interact with local desktop environments on macOS and Linux. It abstracts the complexity of GUI interaction, allowing you to programmatically control applications, capture screen state, and automate user-facing tasks through a unified Python interface.
The package sits in an application framework role, bridging between Python code and the native desktop. It depends on websocket and HTTP libraries (websocket-client, websockets, aiohttp) for communication, image processing (pillow) for screen capture and analysis, and pydantic for data validation. It is actively maintained and has no known security vulnerabilities, though its license status remains unconfirmed in the public metadata.
Use it for
- Automate repetitive GUI workflows on macOS or Linux without writing platform-specific scripts
- Build testing frameworks that validate application behavior by interacting with the desktop UI
- Create headless agents that control local applications programmatically for integration or data extraction
- Develop sandboxed automation tasks that need to interact with multiple applications in sequence
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to automate desktop interaction on macOS or Linux and are comfortable with the unclear license status.
The package is actively maintained, has low install friction, carries no known vulnerabilities, and offers a unified interface to a complex problem. Verify the license terms and system requirements before committing to production use.
Install
cua-computer on PyPI
Before you install
Low install friction with a pure-Python wheel distribution. Active maintenance status as of 57 days since latest release. Seven runtime dependencies including pillow, websocket-client, websockets, aiohttp, cua-core, pydantic, and mslex introduce moderate dependency weight.
Requires Python >=3.12,<3.14. Designed for local macOS or Linux environments; Windows support status unclear.
License in practice
License treatment is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms before using in proprietary or restricted-license contexts.
Quickstart
pip install cua-computer
from cua_computer import Computer
computer = Computer()
# Use computer object to interact with desktop environmentVerify before relying
- Whether the package requires specific system permissions or sandboxing setup on macOS or Linux beyond standard Python installation
- Performance characteristics and latency when controlling GUI elements across network or local connections
- Whether cua-core is a first-party dependency and what its maintenance and licensing status are
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <3.14,>=3.12 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagespillowwebsocket-clientwebsocketsaiohttpcua-corepydanticmslex |
| Maintenance | Actively maintained 57 days since the last release |
| First released | |
| Downloads | 112,018 / month, #12,384 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: cua_computer-0.5.19-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “GUI interaction library”
- cua-computerCua Computer provides a framework for programmatic interaction with…
- pywinautoAutomate Microsoft Windows GUI interactions by sending mouse and…
- PyAutoGUIPyAutoGUI programmatically controls the mouse and keyboard across…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also cua-agent · cua-core · e2b-desktop · PyAutoGUI · uiautomation · pulp-cli · rest.connector · imgui-bundle · openhands · nvitop