This article provides a step by step deployment guide for using Amazon Kiro CLI on the Azure Cloud Shell.
What is this project trying to Do?
This project aims to configure the Kiro CLI for seamless cross cloud operations across AWS and Azure.
Aren’t You Running on the Wrong Cloud?
Mix and Match — Baby! The Antigravity CLI runs on Azure Cloud Shell:
Azure Cloud Shell with Antigravity CLI
So let’s give Kiro a shot on Azure Cloud Shell!
Azure Cloud Shell
Azure Cloud Shell is a browser-based, authenticated terminal for managing Azure resources, accessible directly through the Azure portal, shell.azure.com, or the mobile app. It provides a preconfigured environment with Bash or PowerShell, eliminating local installation of tools. It runs on a temporary, secure, Linux-based host.
The full background information on the Cloud Shell is here:
https://azure.microsoft.com/en-us/get-started/azure-portal/cloud-shell
More information is available here:
Get started with Azure Cloud Shell
Activating Azure Cloud Shell
The Azure Cloud Shell comes preinstalled on all Azure Accounts.
To access the shell — click the Terminal Icon in the upper right hand corner of the console:
Then activate the full shell:
Note- the disk space in the environment is limited to 5GB- but this is sufficient for Kiro CLI, AWS Cloud Tools, and some customization.
Azure CLI
The Azure Command-Line Interface (CLI) is a cross-platform tool used to connect to Azure and execute administrative commands on Azure resources. It allows you to manage services like virtual machines, databases, and networking through a terminal using interactive prompts or scripts. [1, 2, 3]
More details are available here:
What is the Azure Developer CLI?
william [~]$ az --version
azure-cli 2.86.0
core 2.86.0
telemetry 1.1.0
Extensions:
ml 2.42.0
ssh 2.0.8
Dependencies:
msal 1.35.1
azure-mgmt-resource 24.0.0
Python location '/usr/bin/python3.12'
Config directory '/home/william/.azure'
Extensions directory '/home/william/.azure/cliextensions'
Extensions system directory '/usr/lib/python3.12/site-packages/azure-cli-extensions'
Python (Linux) 3.12.9 (main, Mar 26 2026, 23:21:55) [GCC 13.2.0]
Legal docs and information: aka.ms/AzureCliLegal
Your CLI is up-to-date.
AWS Setup
The AWS CLI provides the basic tools for working with the AWS services:
Check the AWS installation:
william [~]$ aws --version
aws-cli/2.34.57 Python/3.14.5 Linux/6.1.146.1-microsoft-standard exe/x86_64.azurelinux.3
william [~]$
Once the tools are installed — login to the AWS console:
aws login --remote
What is Kiro
Kiro is an agentic, AI-powered Integrated Development Environment (IDE) built by Amazon Web Services (AWS) designed to help developers move from initial concepts to production-ready software. Based on a fork of VS Code (Code OSS), Kiro feels familiar while acting like an autonomous co-developer. [1, 2, 3]
Installing Kiro
The main download site for Kiro is:
https://kiro.dev/
Kiro: Bring engineering rigor to agentic development
for the CLI download — click CLI:
curl -fsSL https://cli.kiro.dev/install | bash
This will download Kiro to Azure Cloud Shell:
Running Kiro
First — authenticate to Kiro. Then confirm:
Verify The Installation
Kiro has full access to the local Azure Cloud Shell Environment:
And check the Azure Tools:
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Resource Group: vm / VM — East US
- Virtual Machine: azure-new (with OS disk, NIC, public IP, NSG, VNet)
- Custom VM image: azure-image-20260310200138
- SSH key: azure_key
- Storage account: xbill
- VM extension: enablevmaccess
Resource Group: a2a-rg-westus2 — West US 2
- Container Registry: a2aacrpenguinv2
- Container App: a2a-app-penguin (in managed environment a2a-env-penguin)
- Container Instance: a2a-container-penguin
- Log Analytics Workspace: workspace-a2argwestus2QVju
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
The project appears to have two main workloads:
1. A traditional VM setup in East US (likely for general compute or dev work)
2. An A2A (Agent-to-Agent) containerized application called "penguin" in West US 2, running on Azure Container Apps
with a private registry and monitoring
Test The AWS Integration
This step tests the Kiro interactions with the remote AWS environment:
Here's a summary of your AWS environment (Account: 106059658660, Region: us-east-1):
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Compute
- EC2: 1 instance (i-03456018d00d13504, t3.small, stopped)
- No active ECS clusters or Elastic Beanstalk environments
Storage
- S3 buckets (5):
- xbill-test — general test bucket (Mar 2026)
- my-adk-comic-artifacts — ADK project artifacts (Apr 2026)
- cdk-hnb659fds-assets-106059658660-us-east-1 — CDK bootstrap assets
- elasticbeanstalk-us-east-1-106059658660 — Beanstalk bucket
- bedrock-agentcore-runtime-106059658660-us-west-2-... — Bedrock AgentCore runtime (us-west-2)
Serverless / AI
- Lambda: 1 function — AgentCore-mcpBedrockRustA-ApplicationAgentMcpServe-rWGgAcNdRUnH (Node.js 22.x)
- No Bedrock Agents currently active
Infrastructure (CloudFormation Stacks)
Several CDK/eksctl stacks showing a history of AI agent experiments:
- AgentCore-mcpBedrockRustAws-default — MCP + Bedrock (Rust, active)
- AgentCore-bedrocksre-default — Bedrock SRE agent
- AgentCore-AdkBedrockPythonAws-default — ADK + Bedrock (Python)
- AgentCore-adkbedrock-default — ADK Bedrock
- AgentCore-McpBedrockPythonAws-default — MCP + Bedrock (Python)
- CDKToolkit — CDK bootstrap
- EKS clusters: mcp-eks-cluster, adkui-eks-cluster, biometric-scout-cluster (all stacks present but clusters not
currently listed as active)
Networking
- 2 VPCs: default (172.31.0.0/16) + eksctl-mcp-eks-cluster-cluster/VPC (192.168.0.0/16)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Theme: This environment is heavily focused on AI agent development — multiple iterations of Bedrock-based agents
using ADK (Agent Development Kit) and MCP (Model Context Protocol), deployed via CDK and EKS.
So Why? Just Why? Why Mix and Match Cloud Setups?
Kiro was used to summarize the advantages of the approach:
summarize the benefits of using Kiro from the Azure Cloud Shell
Based on what I can observe from your actual environment, here are the practical benefits of using Kiro from Azure
Cloud Shell:
Multi-cloud visibility in one place
You're already authenticated to Azure, AWS, and GCP from this shell. Kiro can query and reason across all three
simultaneously — as demonstrated just now, summarizing both your Azure and AWS environments in a single
conversation.
Natural language over CLI complexity
Instead of remembering az resource list vs aws ec2 describe-instances vs gcloud compute instances list, you just
ask. Kiro picks the right CLI and flags.
Context-aware assistance
Kiro reads your actual environment — your subscription, resource groups, stacks, buckets — before answering.
Responses are grounded in your real infrastructure, not generic examples.
Persistent toolchain already installed
Your Cloud Shell has az, aws, gcloud, docker, kubectl, Python, Node, and more pre-installed. Kiro can orchestrate
all of them together to accomplish multi-step tasks (e.g., build → push to ACR → deploy to Container Apps).
No local setup required
Cloud Shell is always-on and pre-authenticated. Kiro runs there without any local install, IDE, or credential
management on your part.
Agentic workflows for infra tasks
Given your environment (CDK stacks, EKS, Container Apps, Bedrock agents), Kiro can help write IaC, debug
deployments, compare cloud costs, or scaffold new agent projects — all from the same terminal session.
Summary
The Azure Cloud Shell provides an environment for rapid prototyping Agentic development. With some configuration and customization- it provides core functionality cross cloud using the Kiro CLI.
Top comments (0)