AWS Emulator: Open-source tool for testing AWS apps locally, built by autonomous AI agents
Amazon Web Services has released AWS Emulator, a free tool that simulates AWS services on a developer’s laptop, a development server or in a continuous integration (CI) pipeline.
Amazon Web Services has released AWS Emulator, a free tool that simulates AWS services on a developer’s laptop, a development server or in a continuous integration (CI) pipeline.
The company says autonomous AI agents wrote the tool entirely, with no code written or reviewed by its engineers; there is no more service fee, users pay for AWS resources when they deploy applications on AWS.
It reports failures and groups problems that appear to share an underlying cause, and the third team fixes the reported issues, with each agent responsible for one problem.
By default, the emulator sends anonymous usage and error data to AWS, though users can disable this reporting.
They can run integration tests in a CI pipeline without an AWS account or resources, or prototype applications locally with AI coding agents before deploying them on AWS.
The documentation advises using one region and one account for all requests to an emulator instance because it does not keep resources separate by region or account.
We could do this because the guardrails we’ve put in place gave the agents space to work independently and us the trust that they don’t color outside these lines, Matthew Goldberg, a senior principal engineer at AWS, explained.
The growing collection contains tens of thousands of tests that can be replayed without contacting AWS again.
(Source: AWS) The first team creates tests from publicly available AWS API specifications and verifies them against real AWS services, and the code repository contains every issue filed by the agents, organized into fixed and unresolved folders.
Before a change enters the main codebase, it must pass build checks and reviews by other agents for coding standards, security and fidelity, and changes that fail any of these checks go back for revision.
The checks help maintain code quality as the agents make changes.
It does not evaluate AWS Identity and Access Management (IAM) or resource-based policies as AWS does, so it should not be used to test security.
What happened
Amazon Web Services has released AWS Emulator, a free tool that simulates AWS services on a developer’s laptop, a development server or in a continuous integration (CI) pipeline.
The company says autonomous AI agents wrote the tool entirely, with no code written or reviewed by its engineers; there is no more service fee, users pay for AWS resources when they deploy applications on AWS.
What changed
It reports failures and groups problems that appear to share an underlying cause, and the third team fixes the reported issues, with each agent responsible for one problem.
By default, the emulator sends anonymous usage and error data to AWS, though users can disable this reporting.
Who is affected
They can run integration tests in a CI pipeline without an AWS account or resources, or prototype applications locally with AI coding agents before deploying them on AWS.
The documentation advises using one region and one account for all requests to an emulator instance because it does not keep resources separate by region or account.
Why it matters
We could do this because the guardrails we’ve put in place gave the agents space to work independently and us the trust that they don’t color outside these lines, Matthew Goldberg, a senior principal engineer at AWS, explained.
The growing collection contains tens of thousands of tests that can be replayed without contacting AWS again.
Technical details
(Source: AWS) The first team creates tests from publicly available AWS API specifications and verifies them against real AWS services, and the code repository contains every issue filed by the agents, organized into fixed and unresolved folders.
Response
Before a change enters the main codebase, it must pass build checks and reviews by other agents for coding standards, security and fidelity, and changes that fail any of these checks go back for revision.
What security teams should do
It does not evaluate AWS Identity and Access Management (IAM) or resource-based policies as AWS does, so it should not be used to test security.
What to watch next
Watch for revised vendor guidance, fixed versions and mitigation updates.