Skip to main content

Computer-Using Agent (CUA) Operator

Project description

cua-operator

Computer-Using Agent (CUA) Operator

CUA is a new and evolving technology, but it currently lacks good documentation, mature libraries, and easy-to-use tools. While some automation or remote control libraries can work with CUA, they are often hard to set up. This project aims to make it simple for anyone to try out CUA without needing to understand it's internal details or complex configurations. It supports both Windows and macOS, and lets you connect your personal computer to a CUA compatible endpoint and explore the potential of CUA more easily.

Quick Start

Use CUA on your personal computer

Get Python Ready

pip install pillow openai

Run the following Python script and start your journey.

from cua_operator.bridges import OpenAICuaBridge
from cua_operator.operators import LocalCuaOperator
from openai import OpenAI

client = OpenAI(
    api_key="{OPENAI_API_KEY}"
)

operator = LocalCuaOperator(bridge=OpenAICuaBridge(client))
operator.run()

Customization

CUA-Operator is built around two core concepts: operators and bridges. An operator defines how you intend to interact with the CUA, whether through a local machine, a remote device, or potentially a Docker instance. A bridge specifies the service endpoint you connect to, such as OpenAI, with potential support for alternatives like Claude.

All available operators are in the cua_operator.operators namespace.

  • Local CUA Operator: LocalCuaOperator
  • Remote CUA Operator: RemoteCuaOperatorClient and RemoteCuaOperatorServer

All available bridges are in the cua_operator.bridges namespace.

  • OpenAI CUA Bridge: OpenAICuaBridge

Samples: samples

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_operator-0.0.0.tar.gz (16.5 kB view details)

Uploaded Source

Built Distribution

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

cua_operator-0.0.0-py3-none-any.whl (19.7 kB view details)

Uploaded Python 3

File details

Details for the file cua_operator-0.0.0.tar.gz.

File metadata

  • Download URL: cua_operator-0.0.0.tar.gz
  • Upload date:
  • Size: 16.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.5

File hashes

Hashes for cua_operator-0.0.0.tar.gz
Algorithm Hash digest
SHA256 c22e4e0b7540f76e6f111c49d77af648d5ce150d4999007fd77394b3fdb717fb
MD5 69cdc6546213b41c22906812b49dc77e
BLAKE2b-256 228718f23112305324a61cd8c0449e0aef40c800f23ff1ad617edae1eaf303fc

See more details on using hashes here.

File details

Details for the file cua_operator-0.0.0-py3-none-any.whl.

File metadata

  • Download URL: cua_operator-0.0.0-py3-none-any.whl
  • Upload date:
  • Size: 19.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.5

File hashes

Hashes for cua_operator-0.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e1ace207dbdef3ce885e345e29829ef5803131c6b6cd9a6ea6bb6c7b7f3074b7
MD5 36508d0791a610b6972b06033121b7a8
BLAKE2b-256 a06cd982e459d2ddb952a1ec38c34c66d629c34130c02f2a71ee2a2916864de9

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