paper.bib

@misc{ogx,
  author       = {{OGX Contributors}},
  title        = {{OGX} (Open GenAI Stack)},
  year         = {2026},
  url          = {https://github.com/ogx-ai/ogx},
  note         = {Formerly Llama Stack. \url{https://github.com/ogx-ai/ogx}}
}

@misc{ogxk8soperator,
  author       = {{OGX Contributors}},
  title        = {{OGX} Kubernetes Operator},
  year         = {2026},
  url          = {https://github.com/ogx-ai/ogx-k8s-operator},
  note         = {\url{https://github.com/ogx-ai/ogx-k8s-operator}}
}

@inproceedings{arceo2026securing,
  author    = {Arceo, Francisco Javier and Narsing, Varsha Prasad},
  title     = {Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use},
  booktitle = {Proceedings of the ACM Conference on AI and Agentic Systems},
  series    = {ACM Conference on AI and Agentic Systems},
  year      = {2026},
  isbn      = {9798400724152},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  pages     = {862--872},
  numpages  = {11},
  doi       = {10.1145/3786335.3813145},
  url       = {https://doi.org/10.1145/3786335.3813145}
}

@manual{openresponses,
  author       = {{Open Responses Community}},
  title        = {Open Responses Specification},
  year         = {2026},
  url          = {https://www.openresponses.org/},
  note         = {\url{https://www.openresponses.org/}}
}

@inproceedings{kwon2023vllm,
  author    = {Kwon, Woosuk and Li, Zhuohan and Zhuang, Siyuan and Sheng, Ying and Zheng, Lianmin and Yu, Cody Hao and Gonzalez, Joseph E. and Zhang, Hao and Stoica, Ion},
  title     = {Efficient Memory Management for Large Language Model Serving with {PagedAttention}},
  booktitle = {Proceedings of the 29th ACM Symposium on Operating Systems Principles},
  year      = {2023},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  pages     = {611--626},
  doi       = {10.1145/3600006.3613165}
}

@inproceedings{sglang,
  author    = {Zheng, Lianmin and Yin, Liangsheng and Xie, Zhiqiang and Huang, Jeff and Sun, Chuyue and Yu, Cody Hao and Cao, Shiyi and Kober, Christos and Shi, Liang and Wu, Chien-Sheng and Zhang, Hao and Sheng, Ying and Gonzalez, Joseph E. and Stoica, Ion and Ma, Wei-Lin},
  title     = {{SGLang}: Efficient Execution of Structured Language Model Programs},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2024},
  volume    = {37},
  publisher = {Curran Associates, Inc.}
}

@manual{openaiResponsesAPI,
  author       = {{OpenAI}},
  title        = {Responses {API} Reference},
  year         = {2025},
  url          = {https://platform.openai.com/docs/api-reference/responses},
  note         = {\url{https://platform.openai.com/docs/api-reference/responses}}
}

@manual{mcp,
  title        = {Model Context Protocol Specification},
  author       = {{Anthropic}},
  year         = {2026},
  url          = {https://modelcontextprotocol.io/specification/},
  note         = {\url{https://modelcontextprotocol.io/specification/}}
}

@misc{langchain,
  author       = {{LangChain, Inc.}},
  title        = {{LangChain}: Build context-aware reasoning applications},
  year         = {2023},
  url          = {https://github.com/langchain-ai/langchain},
  note         = {\url{https://github.com/langchain-ai/langchain}}
}

@misc{langgraph,
  author       = {{LangChain, Inc.}},
  title        = {{LangGraph}: Build resilient language agents as graphs},
  year         = {2024},
  url          = {https://github.com/langchain-ai/langgraph},
  note         = {\url{https://github.com/langchain-ai/langgraph}}
}

@misc{llamaindex,
  author       = {{LlamaIndex}},
  title        = {{LlamaIndex}: Data framework for {LLM} applications},
  year         = {2022},
  url          = {https://github.com/run-llama/llama_index},
  note         = {\url{https://github.com/run-llama/llama_index}}
}

@misc{crewai,
  author       = {{CrewAI, Inc.}},
  title        = {{CrewAI}: Framework for orchestrating role-playing autonomous {AI} agents},
  year         = {2024},
  url          = {https://github.com/crewAIInc/crewAI},
  note         = {\url{https://github.com/crewAIInc/crewAI}}
}

@misc{haystack,
  author       = {{deepset}},
  title        = {{Haystack}: End-to-end {LLM} framework for building production-ready applications},
  year         = {2023},
  url          = {https://github.com/deepset-ai/haystack},
  note         = {\url{https://github.com/deepset-ai/haystack}}
}

@manual{databricksAgentFramework,
  author       = {{Databricks}},
  title        = {{Mosaic AI Agent Framework}},
  year         = {2025},
  url          = {https://www.databricks.com/product/machine-learning/retrieval-augmented-generation},
  note         = {\url{https://www.databricks.com/product/machine-learning/retrieval-augmented-generation}}
}

@misc{sqlitevec,
  author       = {Alex Garcia},
  title        = {sqlite-vec: A vector search {SQLite} extension},
  year         = {2024},
  url          = {https://github.com/asg017/sqlite-vec},
  note         = {\url{https://github.com/asg017/sqlite-vec}}
}

@article{mlflow,
  author       = {Zaharia, Matei A. and Chen, Andrew and Davidson, Aaron and Ghodsi, Ali and Hong, Sue Ann and Konwinski, Andy and Murching, Siddharth and Nykodym, Tomas and Ogilvie, Paul and Parkhe, Mani and Xie, Fen and Zumar, Corey},
  title        = {{Accelerating the Machine Learning Lifecycle with MLflow}},
  journal      = {IEEE Data Eng. Bull.},
  volume       = {41},
  pages        = {39--45},
  year         = {2018},
  url          = {https://api.semanticscholar.org/CorpusID:83459546}
}

@misc{llamastack,
  author       = {{Llama Stack Contributors}},
  title        = {Llama Stack},
  year         = {2025},
  url          = {https://github.com/llamastack/llama-stack},
  note         = {\url{https://github.com/llamastack/llama-stack}}
}

@misc{ibm_rag_milvus,
  author       = {{IBM Community}},
  title        = {Build {RAG} with {Llama Stack} and watsonx.data {Milvus}},
  year         = {2025},
  url          = {https://community.ibm.com/community/user/blogs/divya13/2025/05/08/build-rag-with-llama-stack-and-watsonxdata-milvus},
  note         = {\url{https://community.ibm.com/community/user/blogs/divya13/2025/05/08/build-rag-with-llama-stack-and-watsonxdata-milvus}}
}

@misc{oracle_oci_ogx,
  author       = {{Oracle}},
  title        = {Accelerating Enterprise Gen {AI} Applications Development on {OCI} with {Llama Stack} and {OCI AI} Blueprints},
  year         = {2025},
  url          = {https://blogs.oracle.com/ai-and-datascience/accelerating-enterprise-gen-ai-applications-development-on-oci-with-llama-stack-and-oci-ai-blueprints},
  note         = {\url{https://blogs.oracle.com/ai-and-datascience/accelerating-enterprise-gen-ai-applications-development-on-oci-with-llama-stack-and-oci-ai-blueprints}}
}

@misc{redhat_ops_agent,
  author       = {{Red Hat}},
  title        = {Generative {AI} Applications with {Llama Stack}: A Notebook-Guided Journey to an Intelligent Operations Agent},
  year         = {2025},
  url          = {https://www.redhat.com/en/blog/generative-ai-applications-llama-stack-notebook-guided-journey-intelligent-operations-agent},
  note         = {\url{https://www.redhat.com/en/blog/generative-ai-applications-llama-stack-notebook-guided-journey-intelligent-operations-agent}}
}

@misc{meta_connect_ogx,
  author       = {{Meta}},
  title        = {Llama Stack: Chapter One},
  year         = {2024},
  url          = {https://developers.facebook.com/m/meta-connect-developer-sessions/llama-stack-chapter-one/},
  note         = {\url{https://developers.facebook.com/m/meta-connect-developer-sessions/llama-stack-chapter-one/}}
}

@misc{ibm_techxchange_ogx,
  author       = {Clyburn, Cedric},
  title        = {Llama Stack: Kubernetes for {RAG} and {AI} Agents in Generative {AI}},
  year         = {2025},
  url          = {https://mediacenter.ibm.com/media/Llama+Stack+Kubernetes+for+RAG+AI+Agents+in+Generative+AI/1_xl78upq2},
  note         = {\url{https://mediacenter.ibm.com/media/Llama+Stack+Kubernetes+for+RAG+AI+Agents+in+Generative+AI/1_xl78upq2}}
}