Metadata-Version: 2.1
Name: meshai
Version: 0.1.4
Summary: MeshAI SDK for decentralized AI model development
Home-page: https://github.com/robbie/meshai-sdk
Author: Robbie (Ravi Tiwari)
Author-email: your.email@example.com
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: transformers
Requires-Dist: pandas
Requires-Dist: scikit-learn
Requires-Dist: numpy
Requires-Dist: joblib
Requires-Dist: Pillow
Requires-Dist: PyPDF2
Requires-Dist: cryptography

# MeshAI SDK

MeshAI SDK is an open-source toolkit designed to decentralize artificial intelligence within organizations, aligning with the data mesh paradigm. It empowers individual teams to develop, train, and maintain their own AI models, enhancing data integration, autonomy, scalability, and flexibility.

## Features

- **Domain-Oriented AI Ownership**: Assign AI agents to specific business domains using the `DomainManager`.
- **Data Proximity**: (Upcoming) Deploy AI agents close to data sources with provided deployment tools and guidelines.
- **Interoperability**: (Upcoming) Facilitate communication between AI agents across domains.
- **Governance and Compliance**: Ensure adherence to standards with integrated logging and audit trails.
- **Scalability and Flexibility**: (Upcoming) Enable scalable AI development with distributed training capabilities.
- **Support for Multiple Data Types**: Handle text, images, numerical data, and more.
- **Pre-trained Model Integration**: Easily load and fine-tune pre-trained models from popular libraries.
- **Custom Model Support**: Allow users to integrate their own models and architectures.
- **Extensibility**: Modular design allows for easy addition of new features and data handlers.

## Installation

You can install the MeshAI SDK from PyPI:

```bash
pip install meshai
