Skip to main content

A reusable Python SDK for controlling a computer-using agent in a virtual desktop.

Project description

CUA Agent SDK

A reusable, pip-installable Python SDK for controlling a computer-using agent in a virtual desktop (e.g., Docker, VNC, or any custom environment) using OpenAI CUA models. The SDK is fully configurable, class-based, and easy to integrate into any Python project.


🚀 Installation

Install from source:

pip install .

or (when published):

pip install cua-sdk

🛠️ Usage

from cua_sdk import ComputerAgent

agent = ComputerAgent(
    openai_api_key="sk-...",
    llm_model="computer-use-preview",
    docker_container_name="cua-image",
    docker_display=":99",
    sleep_time=0.2,
    screen_width=800,
    screen_height=600,
    screenshot_format="jpeg",
    screenshot_detail="low",
    prompt_path="prompt.txt",
    # ...any other config
)

agent.start()
agent.send_prompt("Apply to this job: https://company.com/apply/123")
agent.change_config(llm_model="gpt-4.1-mini", sleep_time=0.1)
screenshot = agent.get_screenshot()
agent.reset_history()
agent.stop()
  • All parameters can be set via constructor, environment variables, or config defaults.
  • The agent is fully modular and can be used in any Python project.

⚙️ Configuration

Parameters (constructor, env, or config):

  • openai_api_key
  • llm_model
  • docker_container_name
  • docker_display
  • sleep_time
  • screen_width, screen_height
  • screenshot_format (jpeg/png)
  • screenshot_detail (low/high)
  • prompt_path
  • ...and more

Precedence:
Constructor argument > Environment variable > SDK default


📦 Project Structure

cua-sdk/
│
├── cua_sdk/
│   ├── __init__.py
│   ├── agent.py           # Main class-based SDK
│   └── ... (other helpers)
├── setup.py
├── pyproject.toml
├── README.md
├── requirements.txt
├── examples/              # (optional) usage scripts
├── docker/                # (optional) Dockerfiles, utilities

📝 Notes

  • The SDK does not require Docker or any specific environment—just pass the right config for your use case.
  • Example Dockerfiles and scripts are provided in /docker for convenience, but are not required for SDK use.
  • You can use your own prompt templates, models, and agent configuration.

🧑‍💻 Author


Build universal, automated desktop agents with the CUA Agent SDK!

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cua_sdk-0.1.0.tar.gz (11.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cua_sdk-0.1.0-py3-none-any.whl (14.4 kB view details)

Uploaded Python 3

File details

Details for the file cua_sdk-0.1.0.tar.gz.

File metadata

  • Download URL: cua_sdk-0.1.0.tar.gz
  • Upload date:
  • Size: 11.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.1

File hashes

Hashes for cua_sdk-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a17baf16536179271d1199de6e27c91bf1341ae38f8af53e6f0acda2812cb5a1
MD5 de9721900a1bdc44f1ed9e1a9420042a
BLAKE2b-256 88391e897172ce23b8df9f2438d2c41fd2a15d2eaf0b4e2013ea83d6b3429433

See more details on using hashes here.

File details

Details for the file cua_sdk-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: cua_sdk-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 14.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.1

File hashes

Hashes for cua_sdk-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 280edfddf565eb031775eee36449754bd12596d2a2f2ce689c2ce0b45a811c39
MD5 ce324d09223488385e8876cb20f568ce
BLAKE2b-256 f93826014443c34b47d498f30010c0b86f2f798a47ce409bcd915759435b9864

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page