Devyan is an experimental AI-powered software development assistant designed to orchestrate a team of specialized agents for tackling programming tasks. It aims to automate aspects of the software development lifecycle, from architecture design to testing and review, by leveraging OpenAI's GPT models.

How It Works

Devyan utilizes a multi-agent system, powered by the CrewAI framework, to simulate a development team. Each agent is assigned a specific role: Architect, Programmer, Tester, and Reviewer. These agents collaborate by passing information and outputs to one another, mimicking a human development workflow to design, implement, test, and refine software solutions based on user-defined problems.

Quick Start & Requirements

• Installation: Clone the repository, create a virtual environment, and install dependencies using pip install -r requirements.txt.
• Prerequisites: Python 3.7+, OpenAI API Key, and an optional Serper API Key.
• Setup: Requires creating a .env file with your OpenAI API key.
• Usage: Run python main.py and follow the prompts.
• Documentation: https://github.com/theyashwanthsai/Devyan

Highlighted Details

• Orchestrates specialized AI agents (Architect, Programmer, Tester, Reviewer).
• Leverages OpenAI's GPT models for agent capabilities.
• Includes custom tools for file and directory creation.
• Utilizes the CrewAI framework for agent orchestration.

Maintenance & Community

The project is open for contributions via pull requests. A "Todo" list indicates planned features such as adding agent logs, Stack Overflow integration, and code execution capabilities.

Licensing & Compatibility

The repository does not explicitly state a license. Users should verify licensing for commercial use or integration with closed-source projects.

Limitations & Caveats

The project is experimental and marked as a "Todo" for several key features like code execution and detailed agent logging. The current implementation relies heavily on OpenAI's API, incurring associated costs.