agentic-healthcare-assistant

kristenmartino/agentic-healthcare-assistant

★ 0 stars Python 🤖 AI/LLM Updated today

LangGraph-based agentic healthcare assistant — 5-intent router with parallel fan-out, FAISS RAG over patient PDFs, Streamlit UI, MCP server.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agentic-healthcare-a": {
      "command": "uvx",
      "args": [
        "agentic-healthcare-assistant"
      ]
    }
  }
}

Or install with pip: pip install agentic-healthcare-assistant

README Excerpt

Capstone Project 3 for the Simplilearn Applied Generative AI Specialisation. A LangGraph-based agentic assistant that classifies user intent, fans out to up to four specialist branches (booking, records, history, medical search), retrieves over patient PDFs via FAISS-equivalent vector search, and composes a final response. Streamlit UI with cross-session memory via SqliteSaver. QAEvalChain-style evaluation with 10 ground-truth cases at 100% pass.

Tools (11)

actionactordetailsfhirfhir_fixturelanggraphopenpyxloutcomepatient_idsqlitestreamlit

agentic-healthcare-assistant

Quick Install

README Excerpt

Tools (11)

Related AI/LLM Servers