aws-agentcore

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AWS Bedrock AgentCore

Build production-grade AI agents on AWS infrastructure.

在AWS基础设施上构建生产级AI Agent。

Quick Start

快速开始

python

import boto3
from agentcore import Agent, Tool

python

import boto3
from agentcore import Agent, Tool

Initialize AgentCore client

client = boto3.client('bedrock-agent-runtime')

Define a tool

@Tool(name="search_database", description="Search the product database") def search_database(query: str, limit: int = 10) -> dict: # Tool implementation return {"results": [...]}

Create agent

agent = Agent( model_id="anthropic.claude-3-sonnet", tools=[search_database], instructions="You are a helpful product search assistant." )

Invoke agent

response = agent.invoke("Find laptops under $1000")

undefined

response = agent.invoke("Find laptops under $1000")

undefined

AgentCore Components

AgentCore组件

AgentCore provides these primitives:

Component	Purpose
Runtime	Serverless agent execution (framework-agnostic)
Gateway	Convert APIs/Lambda to MCP-compatible tools
Memory	Multi-strategy memory (semantic, user preference)
Identity	Auth with Cognito, Okta, Google, EntraID
Tools	Code Interpreter, Browser Tool
Observability	Deep analysis and tracing

AgentCore提供以下基础组件：

组件	用途
Runtime	无服务器Agent执行（与框架无关）
Gateway	将API/Lambda转换为MCP兼容工具
Memory	多策略记忆（语义、用户偏好）
Identity	与Cognito、Okta、Google、EntraID集成认证
Tools	代码解释器、浏览器工具
Observability	深度分析与追踪

Lambda Tool Integration

Lambda工具集成

python

undefined

python

undefined

Lambda function as tool

import json

def lambda_handler(event, context): action = event.get('actionGroup') function = event.get('function') parameters = event.get('parameters', [])

# Parse parameters
params = {p['name']: p['value'] for p in parameters}

if function == 'get_weather':
    result = get_weather(params['city'])
elif function == 'book_flight':
    result = book_flight(params['origin'], params['destination'])

return {
    'response': {
        'actionGroup': action,
        'function': function,
        'functionResponse': {
            'responseBody': {
                'TEXT': {'body': json.dumps(result)}
            }
        }
    }
}

undefined

import json

def lambda_handler(event, context): action = event.get('actionGroup') function = event.get('function') parameters = event.get('parameters', [])

# Parse parameters
params = {p['name']: p['value'] for p in parameters}

if function == 'get_weather':
    result = get_weather(params['city'])
elif function == 'book_flight':
    result = book_flight(params['origin'], params['destination'])

return {
    'response': {
        'actionGroup': action,
        'function': function,
        'functionResponse': {
            'responseBody': {
                'TEXT': {'body': json.dumps(result)}
            }
        }
    }
}

undefined

Agent Orchestration

Agent编排

python

from agentcore import SupervisorAgent, SubAgent

python

from agentcore import SupervisorAgent, SubAgent

Create specialized sub-agents

research_agent = SubAgent( name="researcher", model_id="anthropic.claude-3-sonnet", instructions="You research and gather information." )

writer_agent = SubAgent( name="writer", model_id="anthropic.claude-3-sonnet", instructions="You write clear, engaging content." )

research_agent = SubAgent( name="researcher", model_id="anthropic.claude-3-sonnet", instructions="You research and gather information." )

writer_agent = SubAgent( name="writer", model_id="anthropic.claude-3-sonnet", instructions="You write clear, engaging content." )

Create supervisor

supervisor = SupervisorAgent( model_id="anthropic.claude-3-opus", sub_agents=[research_agent, writer_agent], routing_strategy="supervisor" # or "intent_classification" )

response = supervisor.invoke("Write a blog post about AI agents")

undefined

supervisor = SupervisorAgent( model_id="anthropic.claude-3-opus", sub_agents=[research_agent, writer_agent], routing_strategy="supervisor" # or "intent_classification" )

response = supervisor.invoke("Write a blog post about AI agents")

undefined

Guardrails Integration

防护栏集成

python

from agentcore import Agent, Guardrail

python

from agentcore import Agent, Guardrail

Define guardrail

guardrail = Guardrail( guardrail_id="my-guardrail-id", guardrail_version="1" )

agent = Agent( model_id="anthropic.claude-3-sonnet", guardrails=[guardrail], tools=[...], )

undefined

guardrail = Guardrail( guardrail_id="my-guardrail-id", guardrail_version="1" )

agent = Agent( model_id="anthropic.claude-3-sonnet", guardrails=[guardrail], tools=[...], )

undefined

AgentCore Gateway

AgentCore网关

Convert existing APIs to MCP-compatible tools:

python

undefined

将现有API转换为MCP兼容工具：

python

undefined

gateway_setup.py

from bedrock_agentcore import GatewayClient

gateway = GatewayClient()

from bedrock_agentcore import GatewayClient

gateway = GatewayClient()

Create gateway from OpenAPI spec

gateway.create_target( name="my-api", type="OPENAPI", openapi_spec_path="./api-spec.yaml" )

Create gateway from Lambda function

gateway.create_target( name="my-lambda-tool", type="LAMBDA", function_arn="arn:aws:lambda:us-east-1:123456789:function:my-tool" )

undefined

gateway.create_target( name="my-lambda-tool", type="LAMBDA", function_arn="arn:aws:lambda:us-east-1:123456789:function:my-tool" )

undefined

AgentCore Memory

AgentCore记忆

python

from agentcore import Agent, Memory

python

from agentcore import Agent, Memory

Create memory with multiple strategies

memory = Memory( name="customer-support-memory", strategies=["semantic", "user_preference"] )

agent = Agent( model_id="anthropic.claude-3-sonnet", memory=memory, tools=[...], )

memory = Memory( name="customer-support-memory", strategies=["semantic", "user_preference"] )

agent = Agent( model_id="anthropic.claude-3-sonnet", memory=memory, tools=[...], )

Memory persists across sessions

response = agent.invoke( "What did we discuss last time?", session_id="user-123" )

undefined

response = agent.invoke( "What did we discuss last time?", session_id="user-123" )

undefined

Official Use Cases Repository

官方用例库

AWS provides production-ready implementations:

Repository: https://github.com/awslabs/amazon-bedrock-agentcore-samples

AWS提供生产级可用的实现方案：

代码库：https://github.com/awslabs/amazon-bedrock-agentcore-samples

Available Use Cases (

02-use-cases/

)

可用用例（

02-use-cases/

）

Use Case	Description
A2A Multi-Agent Incident Response	Agent-to-Agent with Strands + OpenAI SDK
Customer Support Assistant	Memory, Knowledge Base, Google OAuth
Market Trends Agent	LangGraph with browser tools
DB Performance Analyzer	PostgreSQL integration
Device Management Agent	IoT with Cognito auth
Enterprise Web Intelligence	Browser tools for research
Text to Python IDE	AgentCore Code Interpreter
Video Games Sales Assistant	Amplify + CDK deployment

用例	描述
A2A多Agent事件响应	基于Strands + OpenAI SDK的Agent-to-Agent架构
客户支持助手	集成记忆、知识库、Google OAuth
市场趋势Agent	结合LangGraph与浏览器工具
数据库性能分析器	PostgreSQL集成
设备管理Agent	集成IoT与Cognito认证
企业网络智能	基于浏览器工具的调研
文本转Python IDE	AgentCore代码解释器
视频游戏销售助手	Amplify + CDK部署

Quick Start with Use Cases

快速开始使用用例

bash

git clone https://github.com/awslabs/amazon-bedrock-agentcore-samples.git
cd amazon-bedrock-agentcore-samples/02-use-cases/customer-support-assistant

bash

git clone https://github.com/awslabs/amazon-bedrock-agentcore-samples.git
cd amazon-bedrock-agentcore-samples/02-use-cases/customer-support-assistant

Follow README for deployment

undefined

undefined

Resources

资源

Official Samples: https://github.com/awslabs/amazon-bedrock-agentcore-samples
Use Cases: https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/02-use-cases
Tutorials: https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/01-tutorials

官方示例：https://github.com/awslabs/amazon-bedrock-agentcore-samples
用例：https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/02-use-cases
教程：https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/01-tutorials

aws-agentcore

Original

Translation

AWS Bedrock AgentCore

AWS Bedrock AgentCore

Quick Start

快速开始

Initialize AgentCore client

Initialize AgentCore client

Define a tool

Define a tool

Create agent

Create agent

Invoke agent

Invoke agent

AgentCore Components

AgentCore组件

Lambda Tool Integration

Lambda工具集成

Lambda function as tool

Lambda function as tool

Agent Orchestration

Agent编排

Create specialized sub-agents

Create specialized sub-agents

Create supervisor

Create supervisor

Guardrails Integration

防护栏集成

Define guardrail

Define guardrail

AgentCore Gateway

AgentCore网关

gateway_setup.py

gateway_setup.py

Create gateway from OpenAPI spec

Create gateway from OpenAPI spec

Create gateway from Lambda function

Create gateway from Lambda function

AgentCore Memory

AgentCore记忆

Create memory with multiple strategies

Create memory with multiple strategies

Memory persists across sessions

Memory persists across sessions

Official Use Cases Repository

官方用例库

Available Use Cases (02-use-cases/)

可用用例（02-use-cases/）

Quick Start with Use Cases

快速开始使用用例

Follow README for deployment

Follow README for deployment

Resources

资源

Available Use Cases (
`02-use-cases/`
)

可用用例（
`02-use-cases/`
）