Aws Lambda Microvms

This gives Claude the ability to build and operate Firecracker-based microVMs on AWS Lambda with up to 8-hour lifetimes and suspend/resume capabilities. You package an app as a Dockerfile, Lambda snapshots it at boot, then you can run isolated instances with their own HTTPS endpoints. It's built for workloads that need stronger isolation than Lambda functions (multi-tenant code execution, AI agent sandboxes, interactive notebooks) or need features functions can't provide (long sessions, stateful suspend/resume, listening on arbitrary ports, container-level access to FUSE or eBPF). The two-phase model with image builds and runtime instances takes some setup, but you get proper VM isolation with container-like packaging. If your workload fits in 15 minutes and doesn't need session state, regular Lambda functions are simpler.

skills.sh installs: 6.1K
GitHub stars: 3.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aws/agent-toolkit-for-aws --skill aws-lambda-microvms --agent claude-code

Installs into .claude/skills of the current project.

Files

AWS Lambda MicroVMs

The AWS MCP server is recommended for sandboxed execution and audit logging.

AWS Lambda MicroVMs are serverless compute environments that combine Firecracker VM isolation with container-like efficiency. Each MicroVM:

Runs your application as a container inside a Firecracker microVM — you can reproduce the environment locally.
Runs Amazon Linux 2023 as the base OS inside the MicroVM.
Boots from a memory + disk snapshot captured at image build time, so application init is skipped on run.
Has a dedicated, TLS-terminated HTTPS endpoint reachable with an auth token.
Can be suspended and resumed with state preserved; lives up to 8 hours.

Two-resource model:

MicrovmImage — a versioned artifact built from {S3 zip with Dockerfile} + baseImageArn. Each version has per-architecture/chipset Builds.
Microvm — a running instance created (RunMicrovm) from an image version.

Two roles: