Agentic-AI powered wellness platform with multiple specialized agents for mental health support, diet tracking with vision analysis, and personalized exercise planning. Built with DeepSeek, LLaMA, Google models. Used LangChain, LangGraph, Streamlit & Flask.
<h1 align="center">Multi-Agentic Health Assistant</h1> <p align="center">A comprehensive wellness platform powered by AI agents for personalised health management.</p> <hr /> <p align="center"> <img src="data/virtualhealth.png" alt="Virtual Health Assistant" > </p> ## 📋 Overview The Multi-Agentic Health Assistant is an innovative wellness platform that combines the power of multiple Large Language Models (LLMs) and vision models to provide personalized support for physical and mental well-being. The system integrates three specialised AI agents that work together to deliver comprehensive health management through diet tracking, exercise planning, and mental health support. ## 🏗️ System Architecture The platform utilises a multi-agent architecture with three specialised LLM agents, each designed for specific health domains: ### 🧠 Mental Health Agent **Knowledge-based system** for emotional support and mental wellness. - Daily check-ins and emotional support - Guided journaling and motivational prompts - Sentiment analysis and emotion classification - Secure conversation memory with a flagging system - Long-term interaction tracking ### 🥗 Diet Agent **Vision-enabled system** for nutrition analysis and meal planning. - Meal planning and nutritional suggestions - Vision-based analysis of food photos - Nutrient breakdown and diet goal comparison - Dietary preference accommodation - Calorie and macro tracking ### 💪 Exercise Agent **Database-driven system** for fitness planning and tracking. - Personalised workout routine generation - Workout completion and calorie tracking - Weekly difficulty and goal adjustments - Performance data logging - Progress monitoring and analytics ## 🌟 Key Features **Unified Web Interface:** Streamlit/Flask based frontend with intuitive navigation **Multi-Modal AI:** Integration of text and vision models for comprehensive analysis **Personalised Recommendations:** Tailored advice based on individual profiles and goals
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型