AWS Bedrock AgentCore lets you deploy agents as managed containerized runtimes.
This guide shows how to automate this deployment using Pulumi and Docker.
What You'll Deploy
Docker container with your agent code
Amazon ECR to store the image
Bedrock AgentCore Runtime to run your agent
The Setup
- Your Agent Code
from fastapi import FastAPI
from langchain_openai import ChatOpenAI
import uvicorn
app = FastAPI()
@app.post("/invoke")
def invoke(input_data: dict):
llm = ChatOpenAI(model="gpt-4")
response = llm.invoke(input_data["input"])
return {"output": response.content}
if __name__ == "__main__":
uvicorn.run(app, host="0.0.0.0", port=8080)
- Test Locally
export OPENAI_API_KEY="sk-..."
python agents/my_agent/api.py
Test with curl:
curl -X POST http://localhost:8080/invoke \
-H "Content-Type: application/json" \
-d '{"input": "Hello, what is AI?"}'
Example response:
{
"output": "AI, or Artificial Intelligence, refers to..."
}
- Dockerfile
FROM --platform=linux/arm64 ghcr.io/astral-sh/uv:python3.13-bookworm-slim
WORKDIR /app
COPY pyproject.toml uv.lock
COPY agents ./agents
RUN uv sync --frozen --no-cache
EXPOSE 8080
CMD uv run uvicorn agents.my_agent.api:app --host 0.0.0.0 --port 8080
- Build and Push
aws ecr get-login-password --region eu-west-1 | \
docker login --username AWS --password-stdin <account>.dkr.ecr.eu-west-1.amazonaws.com
docker buildx build \
--platform linux/arm64 \
-t <account>.dkr.ecr.eu-west-1.amazonaws.com/my-agents:my_agent_v1 \
--load \
.
docker push <account>.dkr.ecr.eu-west-1.amazonaws.com/my-agents:my_agent_v1
- Deploy with Pulumi
import pulumi
import pulumi_aws as aws
config = pulumi.Config()
region = config.require("aws_region")
bedrock_role_arn = config.require("bedrock_role_arn")
ecr_repo = aws.ecr.get_repository(name="my-agents")
image_uri = f"{ecr_repo.repository_url}:my_agent_v1"
runtime = aws.bedrock.AgentcoreAgentRuntime(
"my_agent_runtime",
agent_runtime_name="my_agent",
agent_runtime_artifact={
"artifact_type": "Docker",
"docker_uri": image_uri,
},
role_arn=bedrock_role_arn,
environment_variables=[
{"name": "AWS_REGION", "value": region},
{"name": "ENV", "value": "production"},
],
)
pulumi.export("runtime_name", runtime.agent_runtime_name)
pulumi.export("runtime_arn", runtime.arn)
- Configure and Deploy
pulumi config set aws:region eu-west-1
pulumi config set aws_region eu-west-1
pulumi config set bedrock_role_arn arn:aws:iam::123456:role/AmazonBedrockExecutionRoleForAgents
pulumi up
Important Notes
ARM64 Required: Bedrock AgentCore only supports ARM64 architecture.
Always use --platform linux/arm64.
Runtime Naming Rules:
IAM Role Permissions:
The Bedrock role needs:
ecr:GetAuthorizationToken
ecr:BatchGetImage
logs:CreateLogGroup, logs:CreateLogStream, logs:PutLogEvents
Viewing Your Agent
Go to AWS Console → Amazon Bedrock AgentCore
Navigate to Agent runtime
Find your runtime in the list
Choose Test endpoint to interact with it
