Md-Emon-Hasan/MediGenius

Advanced multi-agent Medical AI Assistant powered by LangGraph that delivers empathetic, doctor-like responses using a hybrid pipeline of LLM reasoning, RAG from medical PDFs, and intelligent fallback tools. Features Long-term memory with SQLite, dynamic tool routing, and state reasoning for reliable, context-aware consultation.

40
/ 100
Emerging

Implements a specialized five-agent orchestration (Planner, Retriever, Answer Generator, Tool Router, Fallback Handler) via LangGraph that achieves 90%+ factual accuracy and sub-7.3s response times by combining medical RAG from ChromaDB with fallback web searches (Wikipedia, DuckDuckGo) for edge cases. The stack integrates FastAPI backend with React 19 + Vite frontend, SQLite long-term memory for persistent conversation context, and Docker containerization with CI/CD automation for production healthcare deployments.

No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 15 / 25

How are scores calculated?

Stars

16

Forks

4

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Md-Emon-Hasan/MediGenius"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.