[{"data":1,"prerenderedAt":58},["ShallowReactive",2],{"pattern-lambda-microvms-claude-code-agent":3},{"id":4,"title":5,"architectureURL":6,"cleanup":7,"contributors":10,"deploy":12,"description":15,"extension":16,"framework":17,"gitHub":18,"highlight":6,"introBox":24,"language":31,"level":32,"meta":33,"patternArch":34,"resources":39,"s3URL":6,"services":6,"stem":53,"testing":54,"videoId":6,"__hash__":57},"patterns\u002Fpatterns\u002Flambda-microvms-claude-code-agent.json","Claude Code Agent on AWS Lambda MicroVMs",null,{"text":8},[9],"bash cleanup.sh",[11],"content\u002Fcontributors\u002Falexander-vladimirov.json",{"text":13},[14],"bash deploy.sh","Deploy an AWS Lambda MicroVM with the Claude Code CLI, powered by Amazon Bedrock and reachable through an interactive shell.","json","AWS CLI",{"template":19},{"repoURL":20,"templateURL":21,"projectFolder":22,"templateFile":23},"https:\u002F\u002Fgithub.com\u002Faws-samples\u002Fserverless-patterns\u002Ftree\u002Fmain\u002Flambda-microvms-claude-code-agent","serverless-patterns\u002Flambda-microvms-claude-code-agent","lambda-microvms-claude-code-agent","src\u002Fapp.py",{"headline":25,"text":26},"How it works",[27,28,29,30],"This pattern deploys a Lambda MicroVM with the Claude Code CLI installed into the image. The MicroVM is launched with the SHELL_INGRESS network connector, so you connect via an interactive shell (AWS console or a WebSocket client) and run `claude` directly inside the MicroVM.","Claude Code is preconfigured to use Amazon Bedrock with Claude Sonnet 4.6. No API key is stored in the image — the Lambda MicroVM execution role supplies AWS credentials at runtime through the standard AWS SDK credential chain.","The image also bakes in the AWS API MCP server (awslabs.aws-api-mcp-server), letting Claude run live AWS API calls from inside the VM. It uses the same execution-role credentials via the boto3 default chain — no keys — and runs read-only by default (the managed ReadOnlyAccess policy plus READ_OPERATIONS_ONLY). What Claude can do in AWS is controlled entirely by the role's IAM policy.","The MicroVM image is built from a Dockerfile that Lambda executes server-side. During the build the Claude CLI, uv, and the AWS API MCP server are installed, and the application signals readiness via the \u002Fready lifecycle hook, after which Lambda takes a snapshot for rapid resume. The VM auto-suspends when idle and resumes on demand.","Python","200",{},{"icon1":35},{"x":36,"y":36,"service":37,"label":38},50,"lambda-microvms","AWS Lambda MicroVMs",{"bullets":40},[41,44,47,50],{"text":42,"link":43},"AWS Lambda MicroVMs Documentation","https:\u002F\u002Fdocs.aws.amazon.com\u002Flambda\u002Flatest\u002Fdg\u002Flambda-microvms.html",{"text":45,"link":46},"Claude Code on Amazon Bedrock","https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Famazon-bedrock",{"text":48,"link":49},"AWS API MCP Server","https:\u002F\u002Fawslabs.github.io\u002Fmcp\u002Fservers\u002Faws-api-mcp-server",{"text":51,"link":52},"Firecracker - Secure and fast microVMs for serverless computing","https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fopensource\u002Ffirecracker-open-source-secure-fast-microvm-serverless\u002F","patterns\u002Flambda-microvms-claude-code-agent",{"text":55},[56],"See the GitHub repo for detailed testing instructions.","1HBAfuVO4fOeMSN5745hYOokeuMwTBgE6gIgxwpx2Ww",1782470142454]