# How to run Claude Code remotely on Amazon Bedrock AgentCore with security controls

> Original title: Extend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls

- Source: AWS Machine Learning Blog
- Published: 2026-11-06T16:45:58.000Z
- Bad Influence: https://badinfluence.news/items/j8ucvi77s2ctuo1naagjfm9z1
- Original: https://aws.amazon.com/blogs/machine-learning/extend-claude-code-to-remote-sessions-on-amazon-bedrock-agentcore-with-security-controls/

## Summary

AWS explains how to run Claude Code as a remote agent on Amazon Bedrock AgentCore, with each task in its own isolated session inside the customer's AWS account. The sample repository, sample-remote-coding-agent, returns a GitHub pull request for review, and the post describes controls including short-lived GitHub tokens through AgentCore Identity, a prompt guardrail, private VPC networking, and least-privilege IAM. Deployment takes 15–25 minutes and bills while idle, so the post includes cleanup steps.

## Why it matters

The post walks through deploying a remote coding agent with specific security controls, showing how Claude Code tasks can run in isolated sessions and return reviewed pull requests.