综合高级课程 建造生产准备的AI代理 使用Strands Agents SDK。 这个存储库包含6个进步实验室,教授高级能力,包括工具集成,内存持续,模型上下文协议(MCP),以及全面的可观察性.

课程概览

这一高级课程在建立生产准备的AI剂方面提供了基础和先进的专业知识,侧重于剂类,剂环,以及使智能自主系统的组件的完整生态系统. 你将掌握代理AI的核心原理,了解代理如何结合大型语言模型,工具和内存来创建能够自主理解,计划和执行动作的系统.

** 当然主题:** 先进代理架构和生命周期管理

• ** 标准背景协议** - 标准化工具和服务整合 亚马逊-贝德罗克、安特罗皮克、OpenAI和奥拉马
• ** 高级处理** - Hooks,会话管理和谈话策略
• 记忆系统-与FAISS,OpenSearch,和Mem0的长期持续内存

Advanced Strands Agents with MCP

A comprehensive advanced course for building production-ready AI agents using the Strands Agents SDK. This repository contains 6 progressive labs that teach advanced capabilities including tool integration, memory persistence, Model Context Protocol (MCP), and comprehensive observability.

🎯 Course Overview

This advanced course provides foundational and advanced expertise in building production-ready AI agents, focusing on the agent class, agentic loop, and the complete ecosystem of components that power intelligent autonomous systems. You’ll master core principles of agentic AI, understanding how agents combine large language models, tools, and memory to create systems that can understand, plan, and execute actions autonomously.

Course Topics:

• Strands Agents SDK - Advanced agent architecture and lifecycle management
• Model Context Protocol (MCP) - Standardized tool and service integration
• Multi-Provider Configuration - Amazon Bedrock, Anthropic, OpenAI, and Ollama
• Advanced Processing - Hooks, session management, and conversation strategies
• Memory Systems - Long-term persistent memory with FAISS, OpenSearch, and Mem0
• Enterprise Features - Observability, metrics analysis, and performance optimization

Prerequisites: Basic understanding of AI/ML concepts. For beginners, we recommend starting with Getting Started with Strands Agents (Course 1).

📚 Lab Structure

Lab 1: Overview of Strands Agents (12:52)

Files: first_agent.py

Learn fundamental agentic AI concepts and build your first Strands agent:

• Basic agent creation with default configuration (no API keys required)
• Core agent components and execution flow
• Agent result examination (message, metrics, state, stop reasons)
• Dynamic model configuration and system prompt modification
• Conversation history management and message clearing

Lab 2: Model Providers and Configuration (11:59)

Files: anthropic_model.py, bedrock_model.py, ollama_model.py, openai_model.py

Configure agents across multiple LLM providers for flexibility and cost optimization:

• Model architecture overview and provider-specific parameters
• Bedrock model setup with structured output capabilities
• Anthropic model configuration with thinking mode
• Ollama local deployment and OpenAI integration
• Metrics analysis and performance monitoring

Lab 3: Advanced Response Processing with Hooks (13:30)

Files: async_example.py, hook_example_1.py, hook_example_2.py

Implement custom logic to intercept and modify agent behavior at lifecycle points:

• Event-driven hook system and lifecycle management
• Before/after event handling and agent modifications
• Async iterators, callback handlers, and retry logic
• Tool hook examples and precision parameter setup

Lab 4: Tools and MCP Integration (18:55)