AI-powered multi-agent medical assistant with a deterministic safety layer — crisis detection, refused-topic hard-stops, dosage grounding, and post-generation diagnosis verification running before and after every LLM call, backed by parallel RAG, Wikipedia, and Tavily retrieval with symptom and drug-question routing.
multi-agent-systems duckduckgo-search ai-agents healthcare-ai medical-chatbot generative-ai langchain ai-agents-framework knowledge-retrieval langgraph-tools healthcare-ai-assistant ai-healthcare-assistant clinical-assistant doctor-ai fallback-architecture tool-use-ai llm-decision-graph medicalsupervisoragent symptomanalysissubagent druginteractionsubagent
-
Updated
Aug 5, 2026 - Jupyter Notebook