migration-to-aws

v1.5.0

Migrate from GCP or Heroku to AWS — including your entire AI stack. Moves infrastructure (Cloud Run → Fargate, Heroku Dynos → Elastic Beanstalk by default with Fargate/EKS overrides, databases → RDS/Aurora), OpenAI/Gemini workloads to Amazon Bedrock, and agentic systems (LangChain, CrewAI, AutoGen, OpenAI Agents SDK) to AWS-native frameworks. Generates runnable Terraform, migration scripts, provider adapters, and deployment artifacts. Gives honest model-by-model pricing comparisons so you know exactly when Bedrock saves money and when it doesn't.

CodexClaude Code2 Skills4 MCP serversstdioStreamable HTTP

By Amazon Web ServicesLicense: Apache-2.019 GitHub starsUpdated yesterday

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 6 skill or MCP entries
Source updated: Sep 22, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install migration-to-aws for Codex and Claude Code

Installs for the current user

codex plugin marketplace add awslabs/startups
codex plugin marketplace upgrade aws-startup-migration-plugins
codex plugin add migration-to-aws@aws-startup-migration-plugins

Paste and run these commands in a terminal with Codex. They add and refresh the aws-startup-migration-plugins catalog, then install this plugin.

Compatibility: the page URL and API slug “migration-to-aws-2” remain stable.

Codex: migration-to-aws-2@agent-plugin-marketplace → migration-to-aws@aws-startup-migration-plugins

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/awslabs/startups

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is migrate/plugins/migration-to-aws/.

Plugin files

migrate/plugins/migration-to-aws/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/llm-to-bedrock/SKILL.md
├── skills/tf-best-practices/SKILL.md
└── .mcp.json

Included Skills2

llm-to-bedrockskills/llm-to-bedrock/SKILL.md

Use when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. End-to-end: assesses the codebase, then rewrites SDK calls, evaluates output quality against Bedrock, and delivers a ready-to-merge git branch. Not for: agent runtime selection, agentic architecture decisions, or agent migration planning — use agent-advisor for those. Not for standalone Bedrock cost estimates or infrastructure-only migration. REQUIRES the gcp-to-aws skill installed alongside this one — Assess is delegated entirely to it via a cross-skill invocation, with no standalone fallback if gcp-to-aws is absent.

tf-best-practicesskills/tf-best-practices/SKILL.md

Best-practice authoring guidance AND a read-only policy gate for AWS Terraform generated by a migration skill. Load during any phase that writes a terraform/ directory — first as the "what to emit" posture rules + security-baseline spec, then after writing as the deterministic policy verdict. Read-only: it reports whether the generated Terraform passes; it never edits .tf files, never touches .phase-status.json, and never decides phase completion. Complements (does not replace) terraform fmt/init/validate.

MCP servers4

aws-pricing-calculatorstdio

command: npx
args: -y sample-aws-pricing-calculator-mcp@latest

awsknowledgeStreamable HTTP

url: https://knowledge-mcp.global.api.aws

awspricingstdio

command: uvx
args: awslabs.aws-pricing-mcp-server@latest
env.FASTMCP_LOG_LEVEL: ERROR
env.AWS_REGION: us-east-1

temporal-docsStreamable HTTP

url: https://temporal.mcp.kapa.ai

Plugin manifests2

migrate/plugins/migration-to-aws/.codex-plugin/plugin.json

{
  "name": "migration-to-aws",
  "version": "1.5.0",
  "description": "Migrate from GCP or Heroku to AWS — including your entire AI stack. Moves infrastructure (Cloud Run → Fargate, Heroku Dynos → Elastic Beanstalk by default with Fargate/EKS overrides, databases → RDS/Aurora), OpenAI/Gemini workloads to Amazon Bedrock, and agentic systems (LangChain, CrewAI, AutoGen, OpenAI Agents SDK) to AWS-native frameworks. Generates runnable Terraform, migration scripts, provider adapters, and deployment artifacts. Gives honest model-by-model pricing comparisons so you know exactly when Bedrock saves money and when it doesn't.",
  "author": {
    "name": "Amazon Web Services",
    "url": "https://aws.amazon.com"
  },
  "homepage": "https://github.com/awslabs/startups/tree/main/migrate",
  "repository": "https://github.com/awslabs/startups",
  "license": "Apache-2.0",
  "keywords": [
    "aws",
    "gcp",
    "google-cloud",
    "cloud-run",
    "cloud-sql",
    "vertex-ai",
    "gemini",
    "migration",
    "cloud-migration",
    "move-to-aws",
    "switch-to-aws",
    "terraform",
    "fargate",
    "rds",
    "aurora",
    "eks",
    "bedrock",
    "ai-migration",
    "openai",
    "openai-to-bedrock",
    "langchain",
    "langgraph",
    "crewai",
    "autogen",
    "agentic",
    "agents",
    "llm-migration",
    "cost-estimation",
    "cost-comparison",
    "pricing-comparison",
    "agent-runtime",
    "agentcore",
    "lambda-microvms",
    "deploy-ai-agent",
    "agent-architecture",
    "choose-agent-runtime",
    "agentcore-vs-lambda",
    "where-to-run-my-agent",
    "add-agentcore-services",
    "bedrock-migration",
    "openai-to-bedrock-execute",
    "llm-to-bedrock",
    "rewrite-sdk-calls",
    "bedrock-code-rewrite",
    "ai-migration-execute",
    "temporal",
    "temporal-cloud",
    "temporal-workers",
    "temporal-to-aws",
    "durable-execution"
  ],
  "skills": "./skills/",
  "mcpServers": "./.mcp.json",
  "interface": {
    "displayName": "GCP to AWS Migration",
    "shortDescription": "Migrate GCP infrastructure and AI workloads to AWS with architecture mapping, cost analysis, and runnable Terraform.",
    "longDescription": "Point this plugin at your Terraform files, application code, or GCP billing data. It runs a structured 6-phase migration assessment — discovering what you have, asking the right questions, designing the AWS architecture, estimating costs with real pricing data, and generating runnable migration artifacts.\n\nFor AI-focused startups, it detects your entire AI stack (models, agents, tools, orchestration patterns) and recommends three migration paths: retarget (keep your framework, swap models), AgentCore Harness (config-based managed agents), or Strands Agents (AWS-native multi-agent SDK).\n\nGenerates Terraform configurations, migration scripts, provider adapters, harness.json, and documentation — all tailored to your specific stack.",
    "developerName": "Amazon Web Services",
    "category": "Developer Tools",
    "capabilities": [
      "Read",
      "Write"
    ],
    "websiteURL": "https://github.com/awslabs/startups/tree/main/migrate",
    "defaultPrompt": [
      "Migrate my GCP infrastructure to AWS",
      "Migrate my OpenAI app to Amazon Bedrock",
      "Estimate AWS costs for my GCP workload",
      "Generate Terraform for my GCP to AWS migration",
      "Migrate my LangChain app from OpenAI to Bedrock"
    ]
  }
}

migrate/plugins/migration-to-aws/.claude-plugin/plugin.json

{
  "name": "migration-to-aws",
  "version": "1.5.0",
  "description": "This no-cost tool assesses your current cloud provider's usage, geography, and billing data to estimate and compare AWS services and pricing, and recommends migration or continued use of your current provider. Supports GCP and Heroku migrations. AWS pricing is based on current published pricing and may vary over time. The tool may generate a .migration folder containing comparison and migration execution data, which you may delete upon completion or use to migrate to AWS.",
  "author": {
    "name": "Amazon Web Services"
  },
  "license": "Apache-2.0",
  "keywords": [
    "aws",
    "gcp",
    "google-cloud",
    "cloud-run",
    "cloud-sql",
    "vertex-ai",
    "gemini",
    "migration",
    "cloud-migration",
    "move-to-aws",
    "switch-to-aws",
    "terraform",
    "fargate",
    "rds",
    "aurora",
    "eks",
    "bedrock",
    "ai-migration",
    "openai",
    "openai-to-bedrock",
    "langchain",
    "langgraph",
    "crewai",
    "autogen",
    "agentic",
    "agents",
    "llm-migration",
    "cost-estimation",
    "cost-comparison",
    "pricing-comparison",
    "agent-runtime",
    "agentcore",
    "lambda-microvms",
    "deploy-ai-agent",
    "agent-architecture",
    "choose-agent-runtime",
    "agentcore-vs-lambda",
    "where-to-run-my-agent",
    "add-agentcore-services",
    "bedrock-migration",
    "openai-to-bedrock-execute",
    "llm-to-bedrock",
    "rewrite-sdk-calls",
    "bedrock-code-rewrite",
    "ai-migration-execute",
    "temporal",
    "temporal-cloud",
    "temporal-workers",
    "temporal-to-aws",
    "durable-execution"
  ]
}