User Simulation using MAS in Health-Care
A multi-agent simulation that demonstrates clinician‑grade conversational workflows and evidence‑backed recommendations for healthcare using specialist agents, mock wearables, and lab ingestion.
Core trick
Routes messages through specialist LLM agents that call mock wearable and risk tools, attaching evidence references to each reply.
Description
This project implements a multi-agent system (MAS) that simulates a user‑facing healthcare concierge and specialist agents (medical strategist, nutritionist, performance scientist, physiotherapist, orchestrator). The demo includes a WhatsApp‑style chat UI, a health dashboard (wearables, timeline, daily plan), and an evidence pipeline for lab reports and artifacts. Agents are instrumented with tool calls (risk calculators, memory search, wearable fetch) and produce structured outputs with evidence_refs so the frontend can show provenance. The stack is designed for demoability: a Vite + React frontend with Tailwind, a Python backend (FastAPI style) with a MemoryStore (Postgres + Redis) and pluggable LLM provider. Use cases shown: “What’s my heart risk?”, daily plan generation, and upload/interpret lab reports — all with streaming assistant replies and tool‑call badges.
README excerpt
# Elyx Platform 🚀 [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://nextjs.org/) [](https://fastapi.tiangolo.com/) > **Advanced AI-Powered Health Intervention Platform** with multi-agent orchestration, decision traceability, and longitudinal health journey management. ## 🌟 Overview Elyx Platform is a sophisticated health intervention system that demonstrates cutting-edge AI orchestration, decision provenance tracking, and comprehensive health journey visualization. Built for the modern healthcare ecosystem, it provides intelligent agent-based interactions with full traceability and evidence-based decision making. ### ✨ Key Features - **🤖 Multi-Agent AI System** - 6 specialized AI agents with distinct roles and SLA tracking - **📊 Decision Traceability** - Full "why" provenance for every AI decision and recommendation - **🎯 Episode Management** - Structured health episodes with triggers, interventions, and outcomes - **🔬 Experiment Engine** - Hypothesis-driven health interventions with measurement tracking - **📈 Real-time Analytics** - Health metrics visualization and trend analysis - **🔄 Issue Resolution** - Intelligent problem detection and resolution tracking - **👤 User Profili