bowang-lab/MedRAX
MedRAX is a versatile AI agent that integrates advanced chest X-ray analysis tools and multimodal large language models to provide comprehensive medical reasoning and interpretation for complex clinical queries.
Awesome AI Agents › Medical & Healthcare
souvikmajumder26/Multi-Agent-Medical-Assistant
The Multi-Agent Medical Assistant is an advanced AI-powered chatbot system designed to assist healthcare professionals, researchers, and patients with medical diagnosis, healthcare research, and patient interactions. This system leverages a multi-agent architecture where specialized AI agents collaborate to perform tasks such as medical diagnosis, information retrieval, reasoning, and real-time web search to provide accurate and up-to-date medical insights. The assistant integrates large language models (LLMs), computer vision models for medical image analysis (including brain tumor segmentation, chest X-ray disease detection, and skin lesion classification), and retrieval-augmented generation (RAG) techniques using vector databases like Qdrant. It also incorporates human-in-the-loop validation, allowing medical professionals to verify AI-generated diagnoses, ensuring reliability and safety. The system employs advanced RAG techniques such as semantic chunking with structural boundary awareness, hybrid retrieval combining BM25 sparse keyword search with dense vector search, and query expansion with related medical domain terms. Document processing is enhanced using Docling for parsing and extracting text, tables, and images from PDFs, embedding markdown formatted content and LLM-generated image summaries. The architecture supports confidence-based routing and agent-to-agent handoff, enabling efficient multi-agent orchestration through structured graph workflows. Built with a scalable and modular design, the project uses FastAPI for backend services, LangGraph and LangChain for multi-agent orchestration, and Eleven Labs API for speech-to-text and text-to-speech capabilities. The user interface is designed for seamless interaction, and the system is deployable via Docker for ease of setup. This project serves as a comprehensive resource for developers and learners interested in building production-ready AI systems in the medical domain, showcasing robust exception handling, modular code, and integration of cutting-edge AI technologies for healthcare applications.
https://github.com/souvikmajumder26/Multi-Agent-Medical-Assistant
Also in Medical & Healthcare
mims-harvard/TxAgent
TxAgent is an AI agent that leverages multi-step reasoning and a comprehensive toolbox of biomedical tools to provide personalized and precise therapeutic treatment recommendations based on real-time biomedical knowledge and clinical guidelines.
AQ-MedAI/MedResearcher-R1
MedResearcher-R1 is a medical deep research agent plus the knowledge-informed trajectory synthesis pipeline that trained it, turning a domain knowledge graph into multi-hop question-answer pairs and tool-using reasoning trajectories.
gersteinlab/MedAgents
MedAgents is a Multi-disciplinary Collaboration framework leveraging large language models to facilitate zero-shot medical reasoning through expert gathering, iterative analysis, and consensus-driven decision making.
mingze-yuan/Awesome-LLM-Healthcare
A curated repository of research papers and resources reviewing the transformative applications and challenges of Large Language Models in medicine and healthcare.