Research, science & education

Healthcare & medical agents

Healthcare and medical agents handle clinical reasoning, medical question answering, and healthcare workflows, from interpreting chest X-rays to supporting diagnostic conversations. MedRAX shows the clinical side, a reasoning agent built for chest X-ray interpretation, while BianQue targets Chinese-language medical dialogue.

627 agents · most starred first

Top 100 of 627

Awesome-AI-Agents-for-Healthcare★ 1,292

Latest Advances on Agentic AI & AI Agents for Healthcare

MedRAX★ 1,257

MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025

Multi-Agent-Medical-Assistant★ 1,011

⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.

BianQue★ 895

中文医疗对话模型扁鹊(BianQue)

SoulChat★ 774

中文领域心理健康对话大模型SoulChat

DB-GPT★ 713

An LLM Based Diagnosis System (https://arxiv.org/pdf/2312.01454.pdf)

CMLM-ZhongJing★ 539

首个中医大语言模型——“仲景”。受古代中医学巨匠张仲景深邃智慧启迪,专为传统中医领域打造的预训练大语言模型。 The first-ever Traditional Chinese Medicine large language model - "CMLM-ZhongJing". Inspired by the profound wisdom of the ancient Chinese medical master Zhang Zhongjing, it is a pre-trained large language model designed specifically for the field of Traditional Chinese Medicine.

MedResearcher-R1★ 526

MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.

cyber-doctor★ 519

赛博医生项目——”赛博华佗“,基于多模态大模型的多功能智能体,一键搭建本地多模态大模型。接入医疗健康相关的知识图谱和知识库后可以进行疾病初诊,病历分析,专业知识问答等功能,成为你的私人医生。赛博华佗项目能帮助实现医疗资源的跨地域传播,让更多人借助大模型改善健康水平。"Cyber ​​Huatuo" - Easy to build a personal doctor agent based on LLM and Knowledge Graph/Knowledge Database.

cyber-doctor★ 485

赛博医生项目——”赛博华佗“,基于多模态大模型的多功能智能体,一键搭建本地多模态大模型。接入医疗健康相关的知识图谱和知识库后可以进行疾病初诊,病历分析,专业知识问答等功能,成为你的私人医生。赛博华佗项目能帮助实现医疗资源的跨地域传播,让更多人借助大模型改善健康水平。"Cyber ​​Huatuo" - Easy to build a personal doctor agent based on LLM and Knowledge Graph/Knowledge Database.

Health-Care-Chatbot★ 448

It is a medical chatbot that will provide quick answers to FAQs by setting up rule-based keyword chatbots.

Awesome-Agentic-Clinical-Dialogue★ 403

Resource collection of medical agent for clinical dialogue and health

mirobody-eval★ 389

An evaluation harness for medical/health AI agents — reproduce and cover multiple benchmarks under one scoring discipline

AgentClinic★ 381

Agent benchmark for medical diagnosis

MedAgents★ 374

[ACL 2024 Findings] MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning https://arxiv.org/abs/2311.10537

bio★ 357

The world's most powerful open-source bio AI assistant - Access academic literature, clinical trials, drug labels, and more, all through natural conversation.

MedAgentBench★ 352

MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents

MMedAgent★ 279

Learning to Use Medical Tools with Multi-modal Agent

biosecurity-agent★ 277
OpenRehabAgent★ 267

A modular multi-agent framework for video-based pain localisation and adaptive exercise recommendation. This prototype implements the core elements from the OpenRehabAgent paper, including pose synthesis, heuristic pain estimation, a Q-learning agent, safety rules, and feedback tracking

finetuned-qlora-falcon7b-medical★ 263

Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset

healthcare-chatbot★ 263

a chatbot based on sklearn where you can give a symptom and it will ask you questions and will tell you the details and give some advice.

HealthChain★ 231

Python SDK for healthcare AI — typed, validated FHIR tools for agents, real-time EHR connectivity, production deployment ✨ 🏥

VLM-Radiology-Agent-Framework★ 228
biochatter★ 224

Backend library for conversational AI in biomedicine

healthcare-agent-orchestrator★ 217

Facilitates creating modular specialized agents that coordinate across diverse data types and tools like M365 and Teams to assist multi-disciplinary healthcare workflows—such as cancer care.

PharmaLLM-Agent★ 203

Medical LLM agent and MRI segmentation workspace built on PharmaLLM, with LangGraph, vLLM, and BEU-Net.

otc_med_chat_agent★ 198

An AI-powered conversational agent for recommending over-the-counter medications based on user symptoms and needs. Built with Python and integrates a lightweight NLP backend.

MedAgentSim★ 188

MedAgentSim: Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions, MICCAI 2025 (oral and early accepted)

medical-multi-agent-system★ 170

企业级多Agent医疗临床辅助决策系统 | Python/Java/Go三种实现 | LangGraph Pipeline | GraphRAG | FHIR R4 | HIPAA合规 | 完整面试准备材料

CovidPrognosis★ 159

COVID deterioration prediction based on chest X-ray radiographs via MoCo-trained image representations

ClinicalLab★ 154

[NeurIPS 2025] ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World

Ai-Healthcare-Chatbot★ 150

see live demo of chatbot. follow the link

CHA★ 148

Conversational Health Agents: A Personalized LLM-powered Agent Framework

EhrAgent★ 144

[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

MedAgentGym★ 139

[ICLR'26] MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale

dentalpin★ 131

The open source agentic dental software. Built for AI.

hm_editor★ 125

一款轻量级、可扩展的、跨平台的、专为医疗信息化设计的电子病历编辑器内核,为EMR(电子病历系统)提供专业的结构化病历编辑与AI接入解决方案。

ReasonMed★ 124

ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning

patient-psi★ 121

PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals (EMNLP 2024)

DiagGym★ 116

A virtual clinical environment for self‑evolving LLM diagnostic agents.

cardiobot★ 114

Cardio chatbot is trained on carefully curated datasets related to cardiovascular diseases. It provides context-aware, medically relevant responses to user queries, supporting both patients and practitioners in understanding symptoms, treatment options, and preventive measures. The model is fine-tuned to stay within the scope of cardiovascular heal

MedSAM-Agent★ 108

MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning

Deep-DxSearch★ 106

An agentic RL framework to enhance retreival-augmented reasoning in Diagnostic Policy

DoctorAgent-RL★ 106

DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue

hospital_multiagent_system★ 101

医疗问诊系统multi-agent框架

AnnaAgent★ 100

Dynamic evolution agent system with multi-session memory for realistic seeker simulation in psychological counseling.

AgentStack-HealthcareAgent★ 100

An healthcare based example of how to build and deploy an A2A Agent that calls other A2A Agents on the open source platform Agent Stack by IBM Research.

autonomous-oncology-board★ 100

gradio medical-ai oncology multi-agent amd rocm gigapath llama

OpenLinkage★ 99

【软件创新大赛国三】🧩 An open-source multi-agent framework for intelligent health management, powered by the Linkage ecosystem.

COVID19_AgentBasedSimulation★ 95

COVID-ABS: An Agent-Based Model of COVID-19 Epidemic to Simulate Health and Economic Effects of Social Distancing Interventions

RenShu-AI★ 95

Renshu AI is a multi-agent Traditional Chinese Medicine (TCM) consultation system featuring a decoupled front-end and back-end architecture built with FastAPI and React, utilizing the "Harness" paradigm. It aims to address key pain points in TCM consultations—such as low intent recognition accuracy, the fragmentation of structured and unstructured

niehaixia★ 93

倪海厦skill · 经方中医AI 将经方大师倪海厦的完整中医思维体系注入 AI Agent

Chinese-MedQA-Qwen2★ 90

基于Qwen2+SFT+DPO的医疗问答系统,项目中使用了自定义的 SFTTrainer/DPOTrainer/TRPOTrainer用于训练,其次,项目还调用各种知识库工具(neo4j, milvus, LDA, 等)进行自动化训练数据生成。另外,使用 vllm 用于推理和部署训好的模型, 该模型会通过 vllm API 来接入一个基于 embedder + Reranker 的 RAG 系统。另外还参考 MDAgents 论文实现了一个多智能体会诊系统,同样也支持 vllm api 接入。

Multi-agent-conversation-for-disease-diagnosis★ 90

This depository introduces a multi-agent conversation framework which facilitates in depth conversation among LLMs for complex disease diagnosis.

awesome-medical-imaging-agents★ 89

Awesome list for medical imaging agents: radiology agents, pathology agents, segmentation agents, medical VLM agents, self-evolving agents, benchmarks, datasets, tools, and papers.

Health-Flow★ 88

基于多模态大模型(VLM)与 Agent 架构的医疗辅助系统,针对医疗场景下复杂单据解析难、医学逻辑容易产生幻觉的核心痛点,提供体检报告解析、生化指标趋势分析、多专科智能分诊等服务。

mAIstro★ 87

A multi-agent framework for autonomous end-to-end development of radiomics and deep learning models for medical imaging

MedicalAgentsBench★ 86

[Patterns] MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning

Open-MAI-Dx-Orchestrator★ 85

An open source implementation of the paper: "Sequential Diagnosis with Language Models" From Microsoft Built with Swarms Framework

Multilevel_Decomposition_Medical_Agent★ 81

基于LLM和知识图谱的多层级拆解医疗智能体Agent

HasteHealth★ 81

Headless EHR for storing clinical data as FHIR R4 and serving it to apps and AI agents.

chi-bench★ 79

Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

hcls-agent-skills★ 78

Open-source healthcare AI agent skills and life sciences agent skills. 43 skills for medical coding, risk adjustment, claims analytics, quality measures, genomics, imaging, and drug discovery across 13 HCLS domains.

fireagent★ 76

Knowledge-enhanced multimodal Fire Safety Agent with two-hop reasoning, evidence-tree RAG, open-set guardrails, and four-layer memory.

AI-Healthcare-System★ 75

AI Healthcare System & Clinical Data Platform. Combines a Databricks Medallion Lakehouse with TabICLv2 tabular foundation models, calibrated tree ensembles (CatBoost, XGBoost), multi-agent RAG, and clinical decision support portal.

dismech★ 74

Disease Mechanisms KB

PhysicianBench★ 73

The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

ATHENA★ 73

ATHENA-R1: AI agent for treatment reasoning over a biomedical tool universe

ehr-navigator-agent-with-medgemma★ 71

docker medgemma healthcare ehr fhir agent google region:us

MedAgentBoard★ 67

[NeurIPS 2025] MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks

intelligent_consultation★ 67

本平台旨在为用户提供精准、可靠、个性化的健康服务,通过整合多种AI Agent(医学诊断、健康管家、客户服务、运营分析),利用最新的LLM技术与医疗知识图谱,构建智能医疗咨询系统。

openvpm★ 67

Free, open-source, API-first veterinary practice management system (PIMS) — self-hostable, with a built-in AI agent and a real REST API.

Meissa★ 66

Meissa is a multi-modal medical agent, built on trajectory-based agentic behavior distillation framework.

AutoMedBench★ 66

MedAutoBench — Medical AutoResearch Benchmark for Autonomous AI Agents

NLP-chatbot★ 65

A medical chatbot that asks patients about their health and books a doctor's appointment on demand.

medgraph-ai★ 63

Healthcare RAG agent with Neo4j knowledge graphs - Query medical data using LangChain, FastAPI & Streamlit

txgemma-27b-chat★ 63

transformers safetensors gemma2 text-generation therapeutics drug-development

llemr★ 62

NeurIPS'24 DB (Spotlight) | Instruction Tuning Large Language Models to Understand Electronic Health Records

Agent_Hospital★ 62

## AI医院: Multi-Agent 医学智能体 与患者进行多轮对话,提出相关和探索性的问题,推荐适当的医学检查,并在收集足够的信息后做出诊断。设置检查员,他们专门负责与患者互动并提供相关的医学检查结果,确保医生能够获得患者必要的客观信息以做出准确诊断。此外,主治医生负责在整个会话后评估医生的表现。 模拟患者与多名医生之间的互动,包括体检结果的收集和最终诊断。

HealthFlow★ 61

[npj Digital Medicine 2026] HealthFlow: Automating electronic health record analysis via a strategically self-evolving multi-agent framework

MARL-for-Anatomical-Landmark-Detection★ 60

Tensorflow Implementation of Multiple Landmark Detection using Multi-Agent Reinforcement Learning Paper

MedChain★ 60

The repository for "MedChain: Bridging the Gap Between LLM Agents and Real-World Clinical Decision Making"

MAM★ 60

MAM: ModularMulti-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration

HealthCare_ChatBot★ 59

The Chatbot (HealthBot) will try to solve or provide an answer to health-related issues or queries that the user is asking for. We are implementing NLP and ML to improve the efficiency of the chatbot. Tkinter is used as a frontend, and we are creating a desktop application with the help of Tkinter.

remedi★ 57

Find affordable prescription alternatives and patient assistance programs in seconds using FDA data and income eligibility checks.

Disease-Symptom-Prediction-Chatbot★ 56

Healthcare system to predict Diseases based on patient symptoms

MedicalCoderSwarm★ 55

A production-grade multi-agent system for comprehensive medical diagnosis and coding using specialized AI agents.

MDD-5k★ 55

Official Implementation of AAAI 2025 paper "MDD-5k: A New Diagnostic Conversation Dataset for Mental Disorders Synthesized via Neuro-Symbolic LLM Agents"

MediCareAI-Agent★ 54

Multi-Agent Autonomous Medical Collaboration System

MediGenius★ 54

AI-powered multi-agent medical assistant with a deterministic safety layer — crisis detection, refused-topic hard-stops, dosage grounding, and post-generation diagnosis verification running before and after every LLM call, backed by parallel RAG, Wikipedia, and Tavily retrieval with symptom and drug-question routing.

DiagGPT★ 53

Code and data repo for "DiagGPT"

MedSegAgent★ 51

IEEE JBHI 2026 | MedSegAgent: A Universal and Scalable Multi-Agent System for Instructive Medical Image Segmentation

MedicalAI-Platform★ 50

🏥 Med Agentic-AI - 基于多智能体协作的智能医疗分析平台

healthcare-agents★ 50

Portable prompt and SKILL.md pack with 51 specialist AI agents for US healthcare administration workflows.

VetClaw★ 50

The first veterinary AI skill library for OpenClaw. 51 species-aware, safety-first skills + openFDA reference clients for clinical, pharma, and diagnostic workflows.

txgemma-9b-chat★ 50

transformers safetensors gemma2 text-generation therapeutics drug-development

MedVR★ 50

[ICLR'26] MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning

huxishu★ 50

胡希恕(1898-1984)经方临床AI技能 — 将经方传道第一人的六经八纲辨证体系注入AI Agent。基于38万字中日录音增补版讲稿(伤寒论398条+金匮要略22篇),蒸馏为16个六经辨证IF-THEN公式、9组方证鉴别速查表、4大核心心智模型(六经来自八纲/方证是辨证的尖端/正邪交争/胃气为本)、7步条辨法、8个饮食调理模型、剂量换算体系。含398条逐条讲解+22篇金匮详解+7大模块references。基于tcm-distiller中医师蒸馏框架完成。直接激活词:胡希恕、胡老、经方胡希恕、六经八纲、胡希恕怎么看、方证对应。

DeepTumorVQA★ 50

DeepTumorVQA benchmark for VLMs and Agents (10k testing samples)

More in Research, science & education