Skip to content

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

License

Notifications You must be signed in to change notification settings

afanty2021/RD-Agent

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1,032 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

🚀 RD-Agent - 机器学习工程代理

📋 概述

RD-Agent是一个面向机器学习工程(MLE)的自主代理系统,旨在自动化研究和开发流程。该项目在MLE-bench基准测试中表现优异,支持多种场景包括数据科学竞赛、Kaggle竞赛、量化交易和通用模型开发。

✨ 核心特性

  • 🤖 自主进化:基于CoSTEER框架的多进程进化策略
  • 🧠 多场景支持:数据科学、Kaggle、量化交易、通用模型
  • 🔄 多LLM后端:支持OpenAI、Azure OpenAI、Claude、本地模型
  • 📊 性能监控:实时性能指标收集和分析
  • 🐳 Docker化:完整的容器化部署方案
  • 🔧 类型安全:输入验证和命令注入防护

🚀 快速开始

环境要求

  • Python 3.10+
  • Docker(推荐)
  • Git

安装方式

1. 本地开发

# 克隆仓库
git clone https://github.com/afanty2021/RD-Agent.git
cd RD-Agent

# 安装依赖
pip install -e .

2. Docker部署

# 构建并运行
docker build -t rdagent:latest .
docker run -p 8000:8000 rdagent:latest

3. 生产环境

# 使用部署脚本
./scripts/deploy.sh

🔧 配置说明

创建 .env 文件:

# API密钥
OPENAI_API_KEY=your_api_key_here

# 环境变量
PYTHONPATH=/app
RD_AGENT_ENV=development

📋 部署命令

# 开发环境
make dev

# 生产环境
make prod

# Docker环境
make docker

🛠️ 故障排除

常见问题

  1. 端口占用

    lsof -i :8000
  2. 容器问题

    docker logs rdagent
  3. 权限问题

    ls -la /app

📚 文档和资源

🤝 贡献指南

欢迎贡献代码、文档、测试用例和功能建议!

请查看 CONTRIBUTING.md 了解如何参与项目。

About

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.0%
  • Jupyter Notebook 2.0%
  • Other 1.0%