Bedrock AgentCore - Understand AgentCore and Build Your First AgentCore AI Agent in Under an Hour

# Update Linux, install pip, create and activating our environment "myenv"
sudo yum update -y
 sudo yum install python3-pip -y
 python3 -m venv ~/myenv
 source ~/myenv/bin/activate

# Update PATH 
nano ~/.bashrc
- Add to end of file 
export PATH="/<env-path>:$PATH"
PS1='\u@\w\$ '
- Save (ctrl + O)  and exit (Ctrl + x)
source ~/.bashrc

# Install Python 3.11 in your new environment 
sudo dnf update -y
sudo dnf install python3.11 -y
python3.11 —version
 
 
# Install pip for Python 3.11
sudo dnf install python3.11-pip -y
python3.11 -m pip --version

# Add  aliases to your ~/.bashrc file 
nano ~/.bashrc
- Add to end of file 
alias pip="python3.11 -m pip"
alias python="python3.11"
- Save (ctrl + O)  and exit (Ctrl + x)
source ~/.bashrc

# Install Docker and add your user to a Docker group 
- Install Docker 
sudo dnf update -y
sudo dnf install -y docker
sudo systemctl start docker
sudo systemctl enable docker
sudo usermod -aG docker ssm-user
- add your user to a docker group (this example assumes you are using ssm-user, if you choose to use EC2 Instance Connect your user will be ec2-user)
groups ssm-user
newgrp docker
docker ps
docker --version

# Install boto3, bedrock-agentcore, bedrock-agentcore-starter-toolkit, and strands-agents
pip install boto3
pip install bedrock-agentcore-starter-toolkit
pip install bedrock-agentcore
pip install strands-agents


# Create a "projects" directory, create an "agent_1" directory withing "projects" and change directory to agent_1 
cd /usr/tmp
mkdir projects
cd projects
mkdir agent_1
cd agent_1

# Install uv 
curl -LsSf https://astral.sh/uv/install.sh | sh

# Initialize a project using uv 
uv init --python 3.11

# If you get an error like `VIRTUAL_ENV=/home/ec2-user/myenv` does not match the project environment path `.venv`. Try running this command 
uv python pin 3.11

# Let’s add everything that we will need of packages 
uv add 'uvicorn[standard]' strands-agents bedrock_agentcore_starter_toolkit strands-agents-tools bedrock-agentcore


# Import packages
from bedrock_agentcore.runtime import BedrockAgentCoreApp
from strands import Agent

# Define our app referencing the pre-built BedrockAgentCoreApp
app = BedrockAgentCoreApp()
agent = Agent()

# Decorating our app 
@app.entrypoint
def invoke(payload):
    """Process user input and return a response"""
    user_message = payload.get("prompt", "Hello")
    result = agent(user_message)
    return {"result": result.message}

if __name__ == "__main__":
    app.run()

curl -X POST http://localhost:8080/invocations \
-H "Content-Type: application/json" \
-d '{"prompt": "What is the height of the CN Tower?"}'

nano Dockerfile

FROM  ghcr.io/astral-sh/uv:python3.11-bookworm-slim
WORKDIR /app
COPY pyproject.toml uv.lock ./
RUN uv sync --frozen --no-cache
COPY agent_1.py ./
EXPOSE 8080
CMD ["uv", "run", "uvicorn", "agent_1:app", "--host", "0.0.0.0", "--port", "8080"]

- Save (Ctrl + o) , and exit (ctrl + c)


docker buildx create --use

docker buildx build --platform linux/arm64 -t my-agent:arm64 --load .

docker run --platform linux/arm64 -p 8080:8080 \
-e AWS_ACCESS_KEY_ID="$AWS_ACCESS_KEY_ID" \
-e AWS_SECRET_ACCESS_KEY="$AWS_SECRET_ACCESS_KEY" \
-e AWS_SESSION_TOKEN="$AWS_SESSION_TOKEN" \
-e AWS_REGION="$AWS_REGION" \
my-agent:arm64


curl -X POST http://localhost:8080/invocations \
-H "Content-Type: application/json" \
-d '{"prompt": "What is the height of the CN Tower?"}'

# Create an ECR repository:
aws ecr create-repository --repository-name my_agent_1 --region us-west-2

# Login to ECR
- do not forget to replace the <account-id> with your account_id
aws ecr get-login-password --region us-west-2 | docker login --username AWS --password-stdin <account-id>.dkr.ecr.us-west-2.amazonaws.com

# Build and push our docker image to ECR:
- do not forget to replace the <account-id> with your account_id

docker buildx build --platform linux/arm64 -t <account-id>.dkr.ecr.us-west-2.amazonaws.com/my_agent_1:latest --push .

# Verify the image was pushed:

aws ecr describe-images --repository-name my_agent_1 --region us-west-2


{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Sid": "AssumeRolePolicy",
      "Effect": "Allow",
      "Principal": {
        "Service": "bedrock-agentcore.amazonaws.com"
      },
      "Action": "sts:AssumeRole",
      "Condition": {
            "StringEquals": {
                "aws:SourceAccount": "accountId"
            },
            "ArnLike": {
                "aws:SourceArn": "arn:aws:bedrock-agentcore:region:accountId:*"
            }
       }
    }
  ]
}


{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "ECRImageAccess",
            "Effect": "Allow",
            "Action": [
                "ecr:BatchGetImage",
                "ecr:GetDownloadUrlForLayer"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "logs:DescribeLogStreams",
                "logs:CreateLogGroup"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "logs:DescribeLogGroups"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "logs:CreateLogStream",
                "logs:PutLogEvents"
            ],
            "Resource": "*"
        },
        {
            "Sid": "ECRTokenAccess",
            "Effect": "Allow",
            "Action": [
                "ecr:GetAuthorizationToken"
            ],
            "Resource": "*"
        },
        {
            "Effect": "Allow",
            "Action": [
                "xray:PutTraceSegments",
                "xray:PutTelemetryRecords",
                "xray:GetSamplingRules",
                "xray:GetSamplingTargets"
            ],
            "Resource": [
                "*"
            ]
        },
        {
            "Effect": "Allow",
            "Resource": "*",
            "Action": "cloudwatch:PutMetricData",
            "Condition": {
                "StringEquals": {
                    "cloudwatch:namespace": "bedrock-agentcore"
                }
            }
        },
        {
            "Sid": "GetAgentAccessToken",
            "Effect": "Allow",
            "Action": [
                "bedrock-agentcore:GetWorkloadAccessToken",
                "bedrock-agentcore:GetWorkloadAccessTokenForJWT",
                "bedrock-agentcore:GetWorkloadAccessTokenForUserId"
            ],
            "Resource": "*"
        },
        {
            "Sid": "BedrockModelInvocation",
            "Effect": "Allow",
            "Action": [
                "bedrock:InvokeModel",
                "bedrock:InvokeModelWithResponseStream"
            ],
            "Resource": "*"
        }
    ]
}


import boto3

client = boto3.client('bedrock-agentcore-control', region_name='us-west-2')

response = client.create_agent_runtime(
    agentRuntimeName='my_agent_1',
    agentRuntimeArtifact={
        'containerConfiguration': {
            'containerUri': '<account-id>.dkr.ecr.us-west-2.amazonaws.com/my_agent_1:latest'
        }
    },
    networkConfiguration={"networkMode": "PUBLIC"},
    roleArn='arn:aws:iam::<account-id>:role/<AgentRuntimeRole>'
)

print(f"Agent Runtime created successfully!")
print(f"Agent Runtime ARN: {response['agentRuntimeArn']}")
print(f"Status: {response['status']}")

import boto3
import json

agent_core_client = boto3.client('bedrock-agentcore', region_name='us-west-2')
payload = '{"prompt": "What is the height of the CN Tower?"}'

response = agent_core_client.invoke_agent_runtime(
agentRuntimeArn='arn:aws:bedrock-agentcore:us-west-2:<account-id>:runtime/<myStrandsAgent-suffix>',
runtimeSessionId='dfmeoagmreaklgmrkleafremoigrmtesogmtrskhmtkrlshmt', # Must be 33+ chars
payload=payload,
qualifier="DEFAULT"
)

response_body = response['response'].read()
response_data = json.loads(response_body)
print("Agent Response:", response_data)