# Welcome to BiomeAI ## About BiomeAI is a cutting-edge health assistant powered by over 1,000 rigorously curated scientific studies on microbiome science and real-world experiments, designed to help people make smarter, personalized health choices with trustworthy data as its foundation. Built and advised by a team of top experts in gut health and AI, BiomeAI blends deep scientific credibility with participatory governance model to let users test, learn, and figure out what works for them. Every experiment and health insight feeds into a transparent, collective knowledge base that grows with you and the active community. Holding $BIOMEAI grants exclusive first access to the most validated N=10 trial protocols and the next big gut health breakthrough. Top yappers and traders gain a winning chance to earn free microbiome tests by completing community missions, turning engagement into tangible health value. ## BiomeAI's Architecture BiomeAI is built on the [BioAgents](https://github.com/bio-xyz/bioagents) framework powered by [ElizaOS](https://github.com/elizaOS/eliza) and purpose-built for personalized health choices. It layers domain-specific prompts / flows / tools and curated microbiome literature on top of the BioAgents framework. Because BioAgents is under active development, BiomeAI continuously inherits upstream improvements, while adding domain-specific upgrades. This approach ensures BiomeAI's intelligence capabilities compound and grow with every release. BiomeAI extends core components from the BioAgents framework, optimized for the domain of personalized microbiome health choices. Its key intelligence building blocks: * Microbiome report interpretation * Microbiome knowledge graph * OpenScholar fine-tuned on microbiome literature ## Knowledge Graph The knowledge graph acts a semantic representation of microbiome research, . While reasoning, the agent considers if it needs more information to refine its response. In these cases, it queries the knowledge graph to collect further information, enriching the final output with deeper scientific insights.\ In the future anonymised knowledge created by individuals, with their consent, and n=10 trials is going to be connected to the knowledge graph as well. ## OpenScholar BiomeAI's scientific outputs are further refined using a fine-tuned version of [OpenScholar](https://arxiv.org/abs/2411.14199). The model weights used in BiomeAI for the OpenScholar retriever and reranker models can be accessed through the Bio Protocol Huggingface [page](https://huggingface.co/collections/bio-protocol/microbiome-v1-68cc4a22702cefaec8d5ac3c). --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://biomeai.gitbook.io/biomeai-docs/welcome-to-biomeai.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.