Stars
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
TradingAgents: Multi-Agents LLM Financial Trading Framework
LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Antibody Numbering and Antigen Receptor ClassIfication
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
NeurIPS 2023 paper: De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
AI Agents for drug discovery, drug development, and other pharmaceutical R&D
Framework for scientific llm-based multi-agent systems
Language models for drug discovery using torchrl
Multi agent system for drug discovery tasks
Baichuan-M3 Modeling Clinical Inquiry for Reliable Medical Decision-Making
A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
标注自己的数据集，训练、评估、测试、部署自己的人工智能算法
AgenticRAG-ResearchAssistant is an advanced research assistant that uses an agentic RAG approach to answer research queries. It integrates a large language model with external tools for document re…
An agentic multimodal RAG assistant with voice queries, PDF/image understanding, web search, and grounded answers.
基于 Spring Boot 4.1 + Java 21 + Spring AI 2.0 + PostgreSQL + pgvector + RustFS + Redis，实现简历智能分析、AI模拟面试、知识库RAG检索等核心功能。非常适合作为学习和简历项目，学习门槛低。
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
基于 Spring Boot 3.4.5 + Java 21 + Spring Al + LangChain4j + DashScope + Ollama 的智能AI交互系统🤖实战项目，适用于AI应用开发、智能体构建等场景。项目从基础模型调用到RAG知识库问答📚再到工具规划与MCP服务集成，完整覆盖了Al Agent🧠的核心技术，包括多模型接入、上下文记忆、ReAct智能规划、多模态支持🖼️…
本项目是一个基于 LangGraph和大语言模型（LLM）实现的 Agentic RAG (检索增强生成)系统。它融合了动态查询分析和自我纠错机制，能够根据用户问题的复杂度智能地选择最优的策略（直接回答、向量库检索或网络搜索），并对生成的答案进行相关性评估，从而实现更高质量的问答效果。
A Simple Data Augmentation Method for Brain Lesion Segmentation
Pytorch implementation of "LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation"