Back to Details

autonomous-cloud-orchestration

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

AWS Bedrock AgentCore

AWS Bedrock AgentCore

AWS Bedrock AgentCore provides a complete platform for deploying and scaling AI agents with seven core services. This skill guides you through service selection, deployment patterns, and integration workflows using AWS CLI.
AWS Bedrock AgentCore 提供了一个包含七大核心服务的AI Agent部署与扩缩容平台。本技能将引导你使用AWS CLI完成服务选择、部署模式及集成工作流的操作。

AWS Documentation Requirement

AWS文档要求

CRITICAL: This skill requires AWS MCP tools for accurate, up-to-date AWS information.
重要提示：本技能需要AWS MCP工具来获取准确、最新的AWS相关信息。

Before Answering AWS Questions

回答AWS问题前的准备

  1. Always verify using AWS MCP tools (if available):
    • mcp__aws-mcp__aws___search_documentation
      or 
      mcp__*awsdocs*__aws___search_documentation
      - Search AWS docs
    • mcp__aws-mcp__aws___read_documentation
      or 
      mcp__*awsdocs*__aws___read_documentation
      - Read specific pages
    • mcp__aws-mcp__aws___get_regional_availability
      - Check service availability
  2. If AWS MCP tools are unavailable:
    • Guide user to configure AWS MCP: See AWS MCP Setup Guide
    • Help determine which option fits their environment:
      • Has uvx + AWS credentials → Full AWS MCP Server
      • No Python/credentials → AWS Documentation MCP (no auth)
    • If cannot determine → Ask user which option to use
  1. 务必验证（如果可用）使用AWS MCP工具：
    • mcp__aws-mcp__aws___search_documentation
      或 
      mcp__*awsdocs*__aws___search_documentation
      - 搜索AWS文档
    • mcp__aws-mcp__aws___read_documentation
      或 
      mcp__*awsdocs*__aws___read_documentation
      - 阅读特定页面
    • mcp__aws-mcp__aws___get_regional_availability
      - 检查服务区域可用性
  2. 如果AWS MCP工具不可用：
    • 引导用户配置AWS MCP：查看AWS MCP设置指南
    • 帮助用户确定适合其环境的选项：
      • 拥有uvx + AWS凭证 → 完整AWS MCP服务器
      • 无Python/凭证 → AWS文档MCP（无需认证）
    • 若无法确定 → 询问用户使用哪个选项

When to Use This Skill

何时使用本技能

Use this skill when you need to:
  • Deploy REST APIs as MCP tools for AI agents (Gateway)
  • Execute agents in serverless runtime (Runtime)
  • Add conversation memory to agents (Memory)
  • Manage API credentials and authentication (Identity)
  • Enable agents to execute code securely (Code Interpreter)
  • Allow agents to interact with websites (Browser)
  • Monitor and trace agent performance (Observability)
当你需要以下操作时使用本技能：
  • 将REST API部署为AI Agent的MCP工具（Gateway）
  • 在无服务器运行时中执行Agent（Runtime）
  • 为Agent添加对话记忆（Memory）
  • 管理API凭证与身份认证（Identity）
  • 让Agent安全执行代码（Code Interpreter）
  • 允许Agent与网站交互（Browser）
  • 监控和追踪Agent性能（Observability）

Available Services

可用服务

ServiceUse ForDocumentation
GatewayConverting REST APIs to MCP tools
services/gateway/README.md
RuntimeDeploying and scaling agents
services/runtime/README.md
MemoryManaging conversation state
services/memory/README.md
IdentityCredential and access management
services/identity/README.md
Code InterpreterSecure code execution in sandboxes
services/code-interpreter/README.md
BrowserWeb automation and scraping
services/browser/README.md
ObservabilityTracing and monitoring
services/observability/README.md
服务用途文档
Gateway将REST API转换为MCP工具
services/gateway/README.md
RuntimeAgent的部署与扩缩容
services/runtime/README.md
Memory管理对话状态
services/memory/README.md
Identity凭证与访问管理
services/identity/README.md
Code Interpreter在沙箱中安全执行代码
services/code-interpreter/README.md
Browser网页自动化与数据爬取
services/browser/README.md
Observability追踪与监控
services/observability/README.md

Common Workflows

常见工作流

Deploying a Gateway Target

部署Gateway目标

MANDATORY - READ DETAILED DOCUMENTATION: See 
services/gateway/README.md
 for complete Gateway setup guide including deployment strategies, troubleshooting, and IAM configuration.
Quick Workflow:
  1. Upload OpenAPI schema to S3
  2. (API Key auth only) Create credential provider and store API key
  3. Create gateway target linking schema (and credentials if using API key)
  4. Verify target status and test connectivity
Note: Credential provider is only needed for API key authentication. Lambda targets use IAM roles, and MCP servers use OAuth.
必须阅读详细文档：查看
services/gateway/README.md
获取完整的Gateway设置指南，包括部署策略、故障排查和IAM配置。
快速工作流：
  1. 将OpenAPI架构上传至S3
  2. （仅API密钥认证） 创建凭证提供者并存储API密钥
  3. 创建关联架构的Gateway目标（如果使用API密钥则需关联凭证）
  4. 验证目标状态并测试连通性
注意：仅当使用API密钥认证时才需要凭证提供者。Lambda目标使用IAM角色，MCP服务器使用OAuth。

Managing Credentials

凭证管理

MANDATORY - READ DETAILED DOCUMENTATION: See 
cross-service/credential-management.md
 for unified credential management patterns across all services.
Quick Workflow:
  1. Use Identity service credential providers for all API keys
  2. Link providers to gateway targets via ARN references
  3. Rotate credentials quarterly through credential provider updates
  4. Monitor usage with CloudWatch metrics
必须阅读详细文档：查看
cross-service/credential-management.md
获取跨所有服务的统一凭证管理模式。
快速工作流：
  1. 对所有API密钥使用Identity服务的凭证提供者
  2. 通过ARN引用将提供者关联到Gateway目标
  3. 每季度通过更新凭证提供者来轮换凭证
  4. 使用CloudWatch指标监控使用情况

Monitoring Agents

监控Agent

MANDATORY - READ DETAILED DOCUMENTATION: See 
services/observability/README.md
 for comprehensive monitoring setup.
Quick Workflow:
  1. Enable observability for agents
  2. Configure CloudWatch dashboards for metrics
  3. Set up alarms for error rates and latency
  4. Use X-Ray for distributed tracing
必须阅读详细文档：查看
services/observability/README.md
获取全面的监控设置指南。
快速工作流：
  1. 为Agent启用可观测性
  2. 配置CloudWatch仪表盘以查看指标
  3. 为错误率和延迟设置告警
  4. 使用X-Ray进行分布式追踪

Service-Specific Documentation

服务专属文档

For detailed documentation on each AgentCore service, see the following resources:
如需每个AgentCore服务的详细文档，请查看以下资源：

Gateway Service

Gateway服务

  • Overview: 
    services/gateway/README.md
  • Deployment Strategies: 
    services/gateway/deployment-strategies.md
  • Troubleshooting: 
    services/gateway/troubleshooting-guide.md
  • 概述：
    services/gateway/README.md
  • 部署策略：
    services/gateway/deployment-strategies.md
  • 故障排查：
    services/gateway/troubleshooting-guide.md

Runtime, Memory, Identity, Code Interpreter, Browser, Observability

Runtime、Memory、Identity、Code Interpreter、Browser、Observability

Each service has comprehensive documentation in its respective directory:
  • services/runtime/README.md
  • services/memory/README.md
  • services/identity/README.md
  • services/code-interpreter/README.md
  • services/browser/README.md
  • services/observability/README.md
每个服务在其对应的目录下都有全面的文档：
  • services/runtime/README.md
  • services/memory/README.md
  • services/identity/README.md
  • services/code-interpreter/README.md
  • services/browser/README.md
  • services/observability/README.md

Cross-Service Resources

跨服务资源

For patterns and best practices that span multiple AgentCore services:
  • Credential Management: 
    cross-service/credential-management.md
     - Unified credential patterns, security practices, rotation procedures
如需跨多个AgentCore服务的模式和最佳实践：
  • 凭证管理：
    cross-service/credential-management.md
     - 统一凭证模式、安全实践、轮换流程

Additional Resources

额外资源