migration-to-aws Plugin
Plugin Claude Code Development Migration & ModernizationCloud, Deployment & CI/CDAI Agents & AI App DevelopmentThe explanation below is AI-generated. Please verify it against the sources.
migration-to-aws is a plugin for AI coding agents (Claude Code, Codex, and Cursor) that assesses and plans a migration from Google Cloud Platform or Heroku to AWS, including AI/LLM workloads moving to Amazon Bedrock. It scans Terraform files, application code, and billing data to discover resources, then runs a six-phase workflow — Discover, Clarify, Design, Estimate, Generate, and an optional Feedback step — to map services to AWS equivalents, estimate costs, and produce Terraform and migration scripts. According to the source, processing happens locally, so data stays within the user's own environment. A companion plugin, ai-to-aws, is described as handling the actual code rewriting and Bedrock migration execution that migration-to-aws only plans.
Overview
According to the source, this is not a standalone SaaS product but an AI agent plugin (skill) distributed through the awslabs/startups GitHub repository. It is installed into AI coding agents such as Claude Code, Codex, or Cursor to add migration-assessment and planning capability to them.
What you can do with migration-to-aws
- Scan Terraform files, application code, and GCP/Heroku billing data to discover infrastructure and AI/agentic workloads
- Map source services to AWS equivalents (e.g., Cloud Run → Fargate, Cloud SQL → RDS/Aurora, Heroku Dynos → Fargate)
- Generate Terraform files (vpc.tf, compute.tf, database.tf, security.tf, baseline.tf) plus a terraform/README.md
- Select a database migration tool (pg_dump, pgcopydb, or AWS DMS) based on actual database size
- Produce numbered migration scripts for prerequisites validation, data migration, container image migration, secrets migration, and post-migration validation
- Estimate monthly AWS costs across Premium, Balanced, and Optimized tiers using AWS pricing data, compared against current spend
- Detect AI/agentic stacks (models, agents, tools, orchestration patterns) and recommend Bedrock migration paths (retarget, AgentCore Harness, or Strands Agents)
- Generate AI migration artifacts such as harness.json, provider adapters, and deployment scripts
Sources
Original description (English)
Plan a migration from Google Cloud Platform (and OpenAI/Gemini AI workloads) to AWS. Analyzes your Infrastructure-as-Code files, app code, and GCP billing data to discover resources, design an AWS architecture, estimate costs, and generate migration artifacts — including AI-provider mapping to Amazon Bedrock. Processing is local; your data stays in your environment.
History of migration-to-aws
- Plugin Updated Repository of migration-to-aws (https://github.com/awslabs/startups/tree/74c75b973d983abbd415024b6a9893410b2f7470/migrate/plugins/migration-to-aws → https://github.com/awslabs/startups/tree/a7b0d2fda530998f6f8b313d8a3de120031b9023/migrate/plugins/migration-to-aws)
- Plugin Added migration-to-aws