Skip to content

CONTRIBUTING.MD

Latest commit

 

History

History
46 lines (29 loc) · 1.55 KB

CONTRIBUTING.MD

File metadata and controls

46 lines (29 loc) · 1.55 KB

Contributing to Context Engineering for Multi-Agent Systems

First off, thank you for considering contributing to the Context Engine! It’s people like you who help make this a robust, sovereign framework for the Agentic Era.

When contributing to this repository, please first discuss the change you wish to make via the Discussions tab or by opening an issue in the Issues tab.

🧭 Our Architectural Philosophy

This project is built on Glass-Box AI principles. Contributions should prioritize:

🔍 Transparency

Ensure reasoning traces remain observable.

🌐 Domain-Agnosticism

Core engine updates should not include business‑specific rules.

🎯 Fidelity

RAG enhancements must include citation support and sanitization.

🤝 How Can I Contribute?

🐞 Reporting Bugs

  • Use a clear and descriptive title.
  • Describe the exact steps to reproduce the problem.
  • Include snippets of the ExecutionTrace if the error occurred during engine execution.

💡 Suggesting Enhancements

  • Open a discussion in the Ideas & RFCs category.
  • Explain why this enhancement would be useful for a Universal Context Engine.
  • If it involves a new Specialist Agent, describe its MCP message contract.

🔧 Pull Request Process

  1. Fork the repo and create your branch from main.
  2. If you've added code that should be tested, add examples to a new or existing notebook.
  3. Ensure your code follows standard Python formatting (PEP 8).

Thanks again for helping strengthen the Context Engine!