​
Citations & Acknowledgments

AgenticFleet builds upon and is inspired by several outstanding open-source projects and research works.

​
Core Technologies

​
Microsoft AutoGen

AutoGen is a groundbreaking framework for building Large Language Model (LLM) applications with multiple agents. We acknowledge AutoGen for pioneering:

  • Multi-agent conversation frameworks
  • Agent role specialization
  • Conversation management patterns
@misc{autogen2023,
  author = {Microsoft Research},
  title = {AutoGen: Enable Next-Gen Large Language Model Applications},
  year = {2023},
  publisher = {GitHub},
  url = {https://github.com/microsoft/autogen}
}

​
Magentic-One

Magentic-One provides elegant function calling for LLMs. We’re grateful for its contributions to:

  • Type-safe function calling
  • Structured output parsing
  • LLM response validation
@misc{magentic2023,
  author = {Jack Collins},
  title = {Magentic: Elegant Function Calling for Language Models},
  year = {2023},
  publisher = {GitHub},
  url = {https://github.com/jackmpcollins/magentic}
}

​
Chainlit

Chainlit revolutionizes the way we build chat applications. We leverage its capabilities for:

  • Interactive chat interfaces
  • Message streaming
  • UI components
  • User session management
@misc{chainlit2023,
  author = {Chainlit Team},
  title = {Chainlit: Build Python LLM Apps in Minutes},
  year = {2023},
  publisher = {GitHub},
  url = {https://github.com/chainlit/chainlit}
}

​
FastAPI

FastAPI is our foundation for building high-performance APIs. We’re thankful for its:

  • Modern Python web framework
  • Automatic API documentation
  • Type validation
  • Async support
@misc{fastapi2023,
  author = {Sebastián Ramírez},
  title = {FastAPI: Modern Python Web Framework},
  year = {2023},
  publisher = {GitHub},
  url = {https://github.com/tiangolo/fastapi}
}

​
Research Papers

​
Multi-Agent Systems

Our fleet coordination patterns are inspired by research in multi-agent systems:

@article{multiagent2023,
  title={Multi-Agent Systems for Large Language Models: A Survey},
  author={Zhang, et al.},
  journal={arXiv preprint arXiv:2308.11432},
  year={2023}
}

​
Agent Communication

Our agent communication protocols build upon:

@inproceedings{agentcomm2023,
  title={Emergent Communication in Language Models},
  author={Li, et al.},
  booktitle={NeurIPS},
  year={2023}
}

​
Additional Libraries

We also utilize and appreciate:

  • Pydantic: Data validation using Python type annotations
  • SQLAlchemy: Database ORM and management
  • Redis: In-memory data structure store
  • Prometheus: Monitoring and alerting
  • Kubernetes: Container orchestration

​
Contributing Projects

AgenticFleet is made better by contributions from:

  • Open-source community members
  • Research institutions
  • Industry partners
  • Individual developers

​
License

AgenticFleet is licensed under the MIT License. All dependencies and inspirations maintain their respective licenses.

​
Support

If you use AgenticFleet in your research or project, please cite:

@misc{agentic-fleet2024,
  author = {Qredence Team},
  title = {AgenticFleet: Multi-Agent Framework for AI Applications},
  year = {2024},
  publisher = {GitHub},
  url = {https://github.com/qredence/agentic-fleet}
}
Integration Guide