chaoyi-wu

DxEvolver. Python

MedSR-Copilot. Python

superpowers-zh. 🦸 AI 编程超能力 · 中文增强版 — superpowers（116k+ ⭐）完整汉化 + 6 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI 等 16 款 AI 编程工具真正会干活

science-superpowers. Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.

MedSP1000. Python

OligoGym. OligoGym is a python package that streamlines processes involving featurization, training and evaluation of predictive models of oligonucleotide properties. Oligonucleotides include antisense oligonucleotides (ASOs) and small interfering RNAs (siRNAs).

evolver. The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

SciAgent-Skills. 197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.

hermes-agent. The agent that grows with you

MAP. Python

OpenSeeker. OpenSeeker: A search agent with open-source data and models

PyTrial. PyTrial: A Comprehensive Platform for Artificial Intelligence for Drug Development

SkillRL. SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Exomiser. A Tool to Annotate and Prioritize Exome Variants

Agent-Memory-Paper-List. The paper list of "Memory in the Age of AI Agents: A Survey"

Agent-Skills-for-Context-Engineering. A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

langextract. A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

dspy-doc-zh. DSPy中文文档

PhenoLIP. Python

MemBrain. Python

AgentEHR. Agentic System, Tool Use, Electronic Health Record, Large Language Models, Clinical Nature Language Processing

PageIndex. 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

mcp-toolbox. MCP Toolbox for Databases is an open source MCP server for databases.

ToolUniverse. Democratizing AI scientists with ToolUniverse

awesome-claude-skills. A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

helm. Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.

scientific-agent-skills. Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 158 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

TrialMind-SLR. Wang, Z., Cao, L., Danek, B. et al. Accelerating clinical evidence synthesis with large language models. npj Digit. Med. 8, 509 (2025). https://doi.org/10.1038/s41746-025-01840-7

rank_llm. RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.

TREQS. Text-to-SQL Generation for Question Answering on Electronic Medical Records

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

Clinical-Tool-Learning. Python

deepscholar. build and benchmark deep research

Memori. Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

MiroThinker. MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

awesome-medical-mcp-servers. A collection of Medical MCP servers.

M3Builder. The official codes for "M^3Builder: A Multi-Agent System for Automated Machine Learning in Medical Imaging"

ZeroSearch. ZeroSearch: Incentivize the Search Capability of LLMs without Searching

DeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent

O1-Journey. O1 Replication Journey

InnovatorBench. [ICLR 2026]InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research

EHR-R1. Python

biochatter. Backend library for conversational AI in biomedicine

claude-agent-sdk-python. Python

EHRFormer. Python

DeepAnalyze. DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！

PrimeKG. Precision Medicine Knowledge Graph (PrimeKG)

PathPT. [Nature Communications, 2026] The official code for "Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping"

Context-Engineering. "Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspired by Karpathy and 3Blue1Brown for moving beyond prompt engineering to the wider discipline of context design, orchestration, and optimization.

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

agent-lightning. The absolute trainer to light up AI agents.

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

DeepRare. Code implementation of DeepRare (Nature 2026)

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

ChestX-Reasoner. Python

ethos-paper. Jupyter Notebook

MedXpertQA. [ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

ReasoningEval. Official repo of Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains.

INSPECT_public. INSPECT dataset/benchmark paper, accepted by NeurIPS 2023

simple-evals. Python

synthea. Synthetic Patient Population Simulator

ADAS. [ICLR 2025] Automated Design of Agentic Systems

autogen. A programming framework for agentic AI

MetaGPT. 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

MedReason. MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

textgrad. TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

RAG-Gym. Official repository for RAG-Gym

DAPO. An Open-source RL System from ByteDance Seed and Tsinghua AIR

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Search-R1. Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

DDx_CaseReports. impact of lab test results on the accuracy of differential diagnosis (DDx) generated by large language models (LLMs) using clinical case reports

MedRBench. [Nature Communications] The official code for "Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases".

PokeLLMon. Python

pokechamp. Official repository of the spotlight ICML 2025 paper, PokeChamp: an Expert-level Minimax Language Agent.

GeneGPT. Code and data for GeneGPT.

smolagents. 🤗 smolagents: a barebones library for agents that think in code.

RadABench. The official codes for "Can Modern LLMs Act as Agent Cores in Radiology Environments?"

Scrapegraph-ai. Python scraper based on AI

MIMIC-Clinical-Decision-Making-Dataset. Code repository to create the MIMIC-CDM Dataset.

GenerateCT. ECCV 2024 & GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes

ehrapy. Electronic Health Record Analysis with Python.

AgentTorch. large population models

BMTools. Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

ToolLearningPapers.

ToolBench. [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

MedS-Ins. [npj digital medicine] The official codes for "Towards Evaluating and Building Versatile Large Language Models for Medicine"

ReXrank. HTML

RP3D-Diag. Code implementation of RP3D-Diag

RaTEScore. [EMNLP 2024] RaTEScore: A Metric for Radiology Report Generation

KEP. [ECCV 2024 Oral] Knowledge-enhanced pretraining for computational pathology

FlagData. Python

MedLane. Python

long-form-factuality. Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

robustlearn. Robust machine learning for responsible AI

langchain. The agent engineering platform.

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

AgentGPT. 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

Ascle. A Python Natural Language Processing Toolkit for Medical Text Generation

UltraMedical. [NeurIPS 2024 D&B Track, Spotlight] UltraMedical: Building Specialized Generalists in Biomedicine

Taiyi-LLM. Taiyi 2, Biomedical LLM, A Bilingual (Chinese and English) Fine-Tuned Large Language Model for Diverse Biomedical Tasks

Med-PaLM. Towards Generalist Biomedical AI

gpt_bionlp_benchmark.

BLUE_Benchmark. BLUE benchmark consists of five different biomedicine text-mining tasks with ten corpora.

caml-mimic. multilabel classification of EHR notes

esm. Evolutionary Scale Modeling (esm): Pretrained language models for proteins

mimic3-benchmarks. Python suite to construct benchmark machine learning datasets from the MIMIC-III 💊 clinical database.

MEDIQA-M3G-2024. Python

CT-CLIP. Developing Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography

clinical-trial-outcome-prediction. benchmark dataset and Deep learning method (Hierarchical Interaction Network, HINT) for clinical trial approval probability prediction, published in Cell Patterns 2022.

MemDPC. [ECCV'20 Spotlight] Memory-augmented Dense Predictive Coding for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

Existing-Medical-QA-Datasets. Multimodal Question Answering in the Medical Domain: A summary of Existing Datasets and Systems

MIMIC-Diff-VQA. Python

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

InsTag. InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning

Awesome-LLMs-Datasets. Summarize existing representative LLMs text datasets.

FLAN. Python

medalign. MedAlign is a clinician-generated dataset for instruction following with electronic medical records.

LLMDataHub. A quick guide (especially) for trending instruction finetuning datasets

AIONER. AIONER

Prompt-Engineering-Guide. 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

MMedLM. [Nature Communications] The official codes for "Towards Building Multilingual Language Model for Medicine"

discq. Python

GenMedicalEval.

OpenMoE. A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

paper-qa. High accuracy RAG for answering questions from scientific documents with citations

roco-dataset. Radiology Objects in COntext (ROCO): A Multimodal Image Dataset

.github.

pydicom-seg. Python package for DICOM-SEG medical segmentation file reading and writing

nekton. A python package for DICOM to NifTi and NifTi to DICOM-SEG and GSPS conversion

dcmrtstruct2nii. DICOM RT-Struct to mask

SAT. [npj Digital Medicine] The official repository for "Large-Vocabulary Segmentation for Medical Images with Text Prompts"

RP3D-Diag. Code implementation of RP3D-Diag

meditron. Meditron is a suite of open-source medical Large Language Models (LLMs).

FlexLLMGen. Running large language models on a single GPU for throughput-oriented scenarios.

torchio. Medical imaging processing for AI applications.

Medusa. Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

cleanlab. Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Awesome-LLM-Healthcare. The paper list of the review on LLMs in medicine - "Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review".

knowledge-graphs. A collection of research on knowledge graphs

rgrg. Code for the CVPR paper "Interactive and Explainable Region-guided Radiology Report Generation"

LLaVA-Plus-Codebase. LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

SegWithDistMap. How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study

MultiTalent. Implemention of the Paper "MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation"

BioMedLM. Python

natural-instructions. Expanding natural instructions

GPT-4V_Medical_Evaluation.

pixel-lesion-patient-network. Python

RLIPv2. [ICCV 2023] RLIPv2: Fast Scaling of Relational Language-Image Pre-training

RLIP. [NeurIPS 2022 Spotlight] RLIP: Relational Language-Image Pre-training and a series of other methods to solve HOI detection and Scene Graph Generation.

fiftyone. Refine high-quality datasets and visual AI models

BDR-main. Python

DiRA. Official PyTorch Implementation for DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis - CVPR 2022

awesome-llm-powered-agent. Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

deepbgc. BGC Detection and Classification Using Deep Learning

MedCPT. Code for MedCPT, a model for zero-shot biomedical information retrieval.

niicat. This is a tool to quickly preview nifti images on the terminal

pyradiomics. Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks. Support: https://discourse.slicer.org/c/community/radiomics

Viewers. OHIF zero-footprint DICOM viewer and oncology specific Lesion Tracker, plus shared extension packages

RadImageNet. RadImageNet, a pre-trained convolutional neural networks trained solely from medical imaging to be used as the basis of transfer learning for medical imaging applications.

MedQuAD. Medical Question Answering Dataset of 47,457 QA pairs created from 12 NIH websites

VQA-Med-2019. Visual Question Answering in the Medical Domain VQA-Med 2019

CODER. CODER: Knowledge infused cross-lingual medical term embedding for term normalization. [JBI, ACL-BioNLP 2022]

LLMsNineStoryDemonTower. 【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。

anatomy_informed_DA. Python

UniBrain. An offcial implementation for UniBrain: Universal Brain MRI Diagnosis with Hierarchical Knowledge-enhanced Pre-training

gradient-checkpointing. Make huge neural nets fit in memory

RedPajama-Data. The RedPajama-Data repository contains code for preparing large datasets for training large language models.

SAM-Med2D. SAM-Med2D: Bridging the Gap between Natural Image Segmentation and Medical Image Segmentation

medical-data.

OpenBioLink. OpenBioLink is a resource and evaluation framework for evaluating link prediction models on heterogeneous biomedical graph data.

SAM-Med2D. Official implementation of SAM-Med2D

LibriSQA.

Awesome-Medical-Healthcare-Dataset-For-LLM. A curated list of popular Datasets, Models and Papers for LLMs in Medical/Healthcare

StoryGen. [CVPR 2024] Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

Webpilot. Vue

TotalSegmentator. Tool for robust segmentation of >100 important anatomical structures in CT and MR images

RadFM. The official code for "Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data".

med-flamingo. Python

LVM-Med. [NeurIPS 2023] Release LMV-Med pre-trained models

fastmoe. A fast MoE impl for PyTorch

MaskFormer. Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

LLaVA-Med. Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

SegLossOdyssey. A collection of loss functions for medical image segmentation

AbdomenCT-1K. The official repository of "AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?"

MAML. [MICCAI 2021] The official code for "Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation"

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

GPT4RoI. (ECCVW 2025)GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

LLMSurvey. The official GitHub page for the survey paper "A Survey of Large Language Models".

scispacy. A full spaCy pipeline and models for scientific/biomedical documents.

MedSAM. Segment Anything in Medical Images

KAD. Python

MedLSAM. MedLSAM: Localize and Segment Anything Model for 3D Medical Images

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

XrayGPT. [BIONLP@ACL 2024] XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models.

Youku-mPLUG. Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Pre-training Dataset and Benchmarks

ChatRWKV. ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

medicat. Dataset of medical images, captions, subfigure-subcaption annotations, and inline textual references

MING. 明医 (MING)：中文医疗问诊大模型

PMC-Patients. PMC-Patients

Awesome-Visual-Transformer. Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)