> 功能说明: 本技能涵盖 自动化处理、专业的能力支持、专业能力支持、化处理 等核心能力。

aws-agentcore-langgraph

Multi-agent systems on AWS Bedrock AgentCore with LangGraph orchestration. Source: <

Install

pip install bedrock-agentcore bedrock-agentcore-starter-toolkit langgraph
uv tool install bedrock-agentcore-starter-toolkit  # installs agentcore CLI

Quick Start

from langgraph.graph import StateGraph, START
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition  # routing + tool execution
from bedrock_agentcore.runtime import BedrockAgentCoreApp
from typing import Annotated
from typing_extensions import TypedDict

class State(TypedDict):
    messages: Annotated[list, add_messages]

builder = StateGraph(State)
builder.add_node("agent", agent_node)
builder.add_node("tools", ToolNode(tools))  # prebuilt tool executor
builder.add_conditional_edges("agent", tools_condition)  # routes to tools or END
builder.add_edge(START, "agent")
graph = builder.compile()

app = BedrockAgentCoreApp()  # Wraps as HTTP service on port 8080 (/invocations, /ping)
@app.entrypoint
def invoke(payload, context):
    result = graph.invoke({"messages": [("user", payload.get("prompt", ""))]})
    return {"result": result["messages"][-1].content}
app.run()

CLI Commands

Core Patterns

Multi-Agent Orchestration

• Orchestrator delegates to specialists (customer service, e-commerce, healthcare, financial, etc.)
• Specialists: inline functions or separate deployed agents; all share session_id for context

Memory (STM/LTM)

memory import MemoryClient
memory = MemoryClient()
memory.create_event(session_id, actor_id, event_type, payload)  # Store
events = memory.list_events(session_id)  # Retrieve (returns list)

• STM: Turn-by-turn within session | LTM: Facts/decisions across sessions/agents
• ~10s eventual consistency after writes

Gateway Tools

python -m bedrock_agentcore.gateway.deploy --stack-name my-agents --region us-east-1

gateway import GatewayToolClient
gateway = GatewayToolClient()
result = gateway.call("tool_name", param1=value1, param2=value2)

• Transport: Fallback Mock (local), Local connector servers, Production Gateway (Lambda/REST/connector)
• Auto-configures BEDROCK_AGENTCORE_GATEWAY_URL after deploy

Decision Tree

Multiple agents coordinating? → Orchestrator + specialists pattern
Persistent cross-session memory? → AgentCore Memory (not LangGraph checkpoints)
External APIs/Lambda? → AgentCore Gateway
Single agent, simple? → Quick Start above
Complex multi-step logic? → StateGraph + tools_condition + ToolNode

Key Concepts

• AgentCore Runtime: HTTP service on port 8080 (handles /invocations, /ping)
• AgentCore Memory: Managed cross-session/cross-agent memory
• LangGraph Routing: tools_condition for agent→tool routing, ToolNode for execution
• AgentCore Gateway: Transforms APIs/Lambda into connector tools with auth

Naming Rules

• Start with letter, only letters/numbers/underscores, 1-48 chars: my_agent not my-agent

Troubleshooting

References

• • CLI commands, deployment, lifecycle
• [agentcore-runtime.path=references%2Fagentcore-runtime.md&ownerHandle=killerapp) - Streaming, async, observability
• [agentcore-memory.path=references%2Fagentcore-memory.md&ownerHandle=killerapp) - STM/LTM patterns, API reference
• [agentcore-gateway.path=references%2Fagentcore-gateway.md&ownerHandle=killerapp) - Tool integration, connector, Lambda
• [langgraph-patterns.path=references%2Flanggraph-patterns.md&ownerHandle=killerapp) - StateGraph design, routing
• • Example multi-agent architecture

安装与配置

运行环境

• Agent平台: 支持SKILL.md的任意AI Agent( Code / Cursor / Codex / CLI等)
• 操作系统: Windows / macOS / Linux

依赖说明

API Key 配置

• 本Skill基于Markdown指令,无需额外API Key(除内容中明确标注的外部API)

可用性分类

• 分类: MD+execute(纯Markdown指令,部分功能需要exec命令行执行能力)
• 说明: 基于Markdown的AI Skill,通过自然语言指令驱动Agent执行任务

典型场景

不适用于：需要人工判断的复杂决策场景

示例

示例1：基础用法

# 请参考上方使用说明进行配置和调用
result = "ready"
```python
from langgraph.graph import StateGraph, START
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition  # routing + tool execution
runtime import BedrockAgentCoreApp
from typing import Annotated
from typing_extensions import TypedDict

class State(TypedDict):
    messages: Annotated[list, add_messages]

builder = StateGraph(State)
builder.add_node("agent", agent_node)
builder.add_node("tools", ToolNode(tools))  # p

问答整理

Q1: 如何开始使用Aws Agentcore Langgr？

A: 请先阅读使用流程章节，确认环境满足依赖说明中的要求。

Q2: 遇到错误怎么办？

A: 请参考错误处理章节，按照表格中的处理方式操作。

Q3: Aws Agentcore Langgr有什么限制？

A: 请参考已知限制章节了解具体限制。

限制条件

• 依赖云服务，需要网络连接

安全提醒

安全风险防范

使用前请确认已阅读依赖说明章节，确保运行环境满足安全要求。

量化评估

差异分析

重要特性

• 自动化执行: AWS AgentCore与LangGraph部署助手(云写操作需谨慎)
• 文件处理: 支持多种文件格式的读取、解析和写入操作
• API集成: 通过标准化接口调用外部服务并处理响应
• 命令执行: 在安全沙箱中执行系统命令并收集结果

功能介绍

• 自动化执行: AWS AgentCore与LangGraph部署助手(云写操作需谨慎)
• 文件处理: 支持多种文件格式的读取、解析和写入操作
• API集成: 通过标准化接口调用外部服务并处理响应
• 命令执行: 在安全沙箱中执行系统命令并收集结果

```