Skip to main content

kin-kernel contain the default templates of Cells that compose a Kin.

Project description

📖 DigitalKin.ai - KinKernel

PyPI version Python version

Coverage Status

Welcome to the DigitalKin KinKernel ! This package is designed to enable developers to create Cells, which are autonomous agents that can be integrated into the Internet of Agents (IoA) ecosystem powered by DigitalKin.

👀 Overview

The KinKernel provides a framework for creating and managing Cells. Each Cell represents a distinct autonomous agent with a specific role and behavior within the IoA. The KinKernel ensures that all Cells adhere to a standard interface and can communicate effectively within the ecosystem.

💡 Features

  • Abstract base classes for standardizing Cell creation
  • Response models for consistent communication
  • Helper methods for schema information access
  • Configuration management
  • Example Cell implementation

🛠️ Installation

Before installing the KinKernel, ensure you have Python installed on your system. This package requires Python 3.10 or higher.

To install the KinKernel, clone the repository and install the dependencies:

git clone https://github.com/DigitalKin/kin-kernel.git
cd kin-kernel-kit
pip install -r requirements/prod.txt

For development purposes, you may also want to install the development dependencies:

pip install -r requirements/dev.txt

✨ Linter

Execute linters:

   flake8 kinkernel
   black kinkernel --check --diff
   black kinkernel
   mypy kinkernel
   pylint kinkernel

💻 Usage

To create a new Cell, you'll need to subclass the Cell class provided in the kinKernel and implement the required methods and properties.

Here's a simple example of a Cell that processes input data:

from kinkernel import Cell
from pydantic import BaseModel

class MyInputModel(BaseModel):
    value1: int
    value2: str

class MyOutputModel(BaseModel):
    processed_value: int

class MyCell(Cell[MyInputModel, MyOutputModel]):
    role = "Processor"
    description = "Processes input data"
    input_format = MyInputModel
    output_format = MyOutputModel

    def execute(self, input_data: MyInputModel) -> MyOutputModel:
        # Cell-specific logic here
        result = input_data.value1 * 2
        return MyOutputModel(processed_value=result)

You can then instantiate and execute your Cell as follows:

my_cell = MyCell()
input_data = MyInputModel(value1=10, value2="example")
output_data = my_cell.execute(input_data)
print(output_data)

For a more detailed example, refer to the examples/simple_cell_example.py file in the repository.

🧪 Testing

The CDK comes with a set of unit tests to ensure that your Cells work as expected. To run the tests, execute the following command:

pytest

👥 Contribution

Contributions to the KinKernel are welcome! If you have suggestions for improvements or find any issues, please open an issue on our GitHub repository.

🤗 Support

If you have any questions or need support with the KinKernel, please reach out to us at contact@digitalkin.ai.

Thank you for using the DigitalKin Cell Development Kit. We look forward to seeing the innovative Cells you'll create for the Internet of Agents!


© 2023 DigitalKin.ai. All Rights Reserved.

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

kin-kernel-0.0.1.tar.gz (9.5 kB view details)

Uploaded Source

Built Distribution

kin_kernel-0.0.1-py3-none-any.whl (12.2 kB view details)

Uploaded Python 3

File details

Details for the file kin-kernel-0.0.1.tar.gz.

File metadata

  • Download URL: kin-kernel-0.0.1.tar.gz
  • Upload date:
  • Size: 9.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.12

File hashes

Hashes for kin-kernel-0.0.1.tar.gz
Algorithm Hash digest
SHA256 7c5b08b87fdaba0d1d38f09a5df11a509ae288a6a237f47dc948a10b427eeb99
MD5 735c8ba49a7d5996b9b71326463035ac
BLAKE2b-256 98d426f3aa9a38b5ee4475736bf9965a8e16eca086ad9c1a8d04e4d863d67bb1

See more details on using hashes here.

File details

Details for the file kin_kernel-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: kin_kernel-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 12.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.12

File hashes

Hashes for kin_kernel-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 fa0d4c32097a810f85c6ec86f93c3e0f39fb0063e93c8e390e0dd59e3e1e2e95
MD5 65b7b3663d3d78f11071754ea5bc03a8
BLAKE2b-256 4e6f9dc25b4712847a96288fe170f3e4f1bf4c63fef76b34e57e199e6b422fb3

See more details on using hashes here.

Supported by

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