Extend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls

AWS describes running Claude Code remotely on Amazon Bedrock AgentCore, where each task runs in an isolated session and returns results as a GitHub pull request for review.

By AIWI EditorialReviewed by Chayanika DivekarAI-assisted summary · human-reviewed1 min readPublished Nov 6, 2026

Single source1 source

Reality Check

Availability: Availability unclear
Hype-o-meter: Mostly substance
Who it's for: Developers · Enterprises
Do this now: Review the AWS blog to see how to set up Claude Code as a remote agent on Amazon Bedrock AgentCore in your AWS account.
Claims check: The input describes a configuration and workflow but does not specify availability or performance claims.
Corroboration: Single source · 1 source

Key Takeaways

Claude Code can run as a remote agent on Amazon Bedrock AgentCore
Each coding task runs in its own isolated session in your AWS account
Model calls are routed through Amazon Bedrock
Results are delivered as GitHub pull requests to review and merge

AWS outlines how to run Claude Code as a remote agent on Amazon Bedrock AgentCore. In this setup, each coding task executes in its own isolated session within the user’s AWS account, and every model call is routed through Amazon Bedrock. The output of a task is returned as a GitHub pull request that the user reviews and merges.

Why it matters

The described approach places coding-agent work inside the user’s own AWS account with session isolation and model access mediated by Amazon Bedrock. Returning results as pull requests keeps a human review step before changes are merged.

Who should care

Developers and teams using Claude Code who want to run coding tasks remotely on AWS infrastructure, and those managing security controls around agent execution and code changes.

Was this helpful?

Sources & Further Reading

Extend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls — AWS Machine Learning Blog · Nov 6, 2026

Frequently Asked Questions

How are results from a coding task delivered?

Each task returns its result as a GitHub pull request that the user reviews and merges.

Where do the coding tasks run?

Each task runs in its own isolated session within the user's AWS account, with model calls going through Amazon Bedrock.

AI tools in this story

Claude★ 4.7

Browse all AI tools →

Claude Code relaunches Projects to manage multiple AI agents in the cloud — Sep 17, 2026
Preview web apps live as your coding agent builds them with Amazon Bedrock AgentCore runtime — Oct 30, 2026
AI-driven development lifecycle using Amazon Bedrock AgentCore — Sep 3, 2026
Slack is launching collaborative vibe-coding channels — Aug 20, 2026

#agents #claude #coding-assistant #cloud #github