Control GPT Computer Assistant Remotely in 3 Lines of Code

GPT Computer Assistant is an intelligent computer assistant powered by GPT-4o, compatible with Windows, macOS, and Linux platforms. It aims to serve as an alternative to Copilot on Windows.

Key Features of GPT Computer Assistant

Currently, GPT Computer Assistant supports the following capabilities:

• Screen reading
• Clicking on text or icons on the screen
• Moving text or images on the screen
• Text input
• Triggering any key press
• Recording microphone audio
• Recording system audio
• Opening and closing applications
• Opening URLs
• Manipulating the clipboard
• Using search engines
• Writing and running Python scripts
• Writing and running Shell scripts
• Knowledge management

Use Cases for GPT Computer Assistant

Meeting Minutes

GPT Computer Assistant can help record and summarize meetings.

Scheduling

It can assist with managing your calendar and scheduling tasks.

Assisted Reading

The assistant can aid in reading and comprehending text.

Writing Code and Copying to Clipboard

It enables you to generate code snippets and easily copy them to the clipboard.

Getting Started with GPT Computer Assistant

Before installing GPT Computer Assistant, ensure your local Python version is higher than 3.9.

Creating Agents

pip3 install 'gpt-computer-assistant[base]'
pip3 install 'gpt-computer-assistant[agentic]'

from gpt_computer_assistant import Agent, start

manager = Agent(
  role='Project Manager',
  goal='understands project needs and assist coder',
  backstory="""You're a manager at a large company.""",
)

coder = Agent(
  role='Senior Python Coder',
  goal='writing python scripts and copying to clipboard',
  backstory="""You're a python developer at a large company.""",
)


start()

Adding Custom Tools

from gpt_computer_assistant import Tool, start

@Tool
def sum_tool(first_number: int, second_number: int) -> str:
    """Useful for when you need to sum two numbers together."""
    return first_number + second_number

start()

Open API

GPT Computer Assistant supports running as an API to enable remote operation scenarios.

pip3 install 'gpt-computer-assistant[base]'
pip3 install 'gpt-computer-assistant[api]'

computerassistant --api

from gpt_computer_assistant.remote import remote

output = remote.input("Hi, how are you today?", screen=False, talk=False)
print(output)

remote.just_screenshot()

remote.talk("TTS test")

# Other Functionalities
remote.reset_memory()
remote.profile("default")

remote.enable_predefined_agents()
remote.disable_predefined_agents()

remote.enable_online_tools()
remote.disable_online_tools()

For more information, visit the GPT Computer Assistant GitHub repository: https://github.com/onuratakan/gpt-computer-assistant