Get started with AgentCore Runtime using the AgentCore CLI

This page provides a concise workflow for creating and deploying a code-based Strands agent to AgentCore Runtime. For CLI installation, complete prerequisites, project structure, capabilities, observability, and cleanup, see Get started with Amazon Bedrock AgentCore.

Create and test your agent

Create a Python project that uses the Strands Agents SDK and Amazon Bedrock:

agentcore create \
  --name MyProject \
  --template agent-python-strands

The template creates a Python CodeZip Runtime named agent, adds an AgentCore Memory resource, and installs the project dependencies.

You can also run agentcore with no arguments to open the interactive menu. Outside a project, the menu offers create. Inside a project, it offers deploy, invoke, and status. Choosing dev from the menu starts the local server in headless mode. To open the Agent Inspector, run agentcore dev --mode browser.

To choose the template interactively, run agentcore create without options:

Start the Runtime locally and open the Agent Inspector:

cd MyProject
agentcore dev --mode browser

Without --mode browser, agentcore dev defaults to headless mode and streams the Runtime output to your terminal.

Build and deploy your agent

agentcore build
agentcore deploy

Check the deployed resources:

agentcore status

Invoke the deployed Runtime:

agentcore invoke --runtime agent \
  --payload '{"prompt":"Hello, what can you do?"}'

Iterate on app/agent/main.py, test locally, and deploy again when you are ready.

Troubleshoot

For common CLI installation, deployment, configuration, and observability issues, see Troubleshoot.

Next steps

• Get started with Amazon Bedrock AgentCore - use the complete AgentCore CLI workflow.