← Back
AWS ML Blog

Deploying Anthropic Claude apps gateway for AWS for enterprise workloads

15 min read
#anthropic#enterprise#deployment
Level:Advanced
For:AI Engineers
TL;DR

The Claude apps gateway provides a self-hosted governance layer for Anthropic Claude applications on AWS, enabling centralized controls over authentication, model access, cost attribution, and spend enforcement. The reference deployment topology uses AWS Fargate, Amazon RDS, and Amazon Route 53 to manage requests and state. The gateway authenticates to Amazon Bedrock using an AWS IAM role and stores credentials in AWS Secrets Manager. The practical implication for engineers building AI systems is the ability to deploy and manage Claude applications with enterprise-grade security and governance.

⚡ Key Takeaways

  • The Claude apps gateway runs on AWS Fargate inside a virtual private cloud (VPC) and can also run on Amazon EKS or Amazon EC2.
  • The gateway uses Amazon Relational Database Service (Amazon RDS) for PostgreSQL to store short-lived sign-in state and per-user spend counters.
  • The gateway authenticates to Amazon Bedrock using an AWS IAM role and stores credentials in AWS Secrets Manager.
  • The load balancer idle timeout should be configured to exceed the longest expected interval without data to prevent connection termination.
  • The gateway issues a short-lived bearer token, valid for one hour by default, after authentication through an OpenID Connect (OIDC) identity provider.
💡 Why It Matters

The Claude apps gateway provides a critical layer of governance and security for enterprise deployments of Anthropic Claude applications on AWS, enabling administrators to manage authentication, model access, and cost attribution at scale. This is particularly important for large-scale AI deployments, where security and governance are paramount.

✅ Practical Steps

  1. Run the Claude apps gateway using the Claude Code CLI binary with the command `claude gateway --config gateway.yaml`.
  2. Configure the load balancer idle timeout to exceed the longest expected interval without data.
  3. Set up Amazon RDS for PostgreSQL to store short-lived sign-in state and per-user spend counters.

Want the full story? Read the original article.

Read on AWS ML Blog

More like this

Building an AI Text Detector From Scratch

Ahead of AI#llm

Custom reward functions for multi-turn reinforcement learning with Amazon Nova Forge

AWS ML Blog#amazon

Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets

Hugging Face Blog#agents

SpaceXAI releases flagship Grok 4.6 model with advanced reasoning capabilities

SiliconANGLE AI#llm

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING