Radar / AI infrastructure / AWS Emulator
AWS Emulator: a local copy of AWS, written entirely by AI agents
AWS's free, open-source local emulator covering 200+ services from 438 API models, written in Rust, running offline on your laptop or in CI with no AWS account — and, remarkably, every line of code was written and tested by autonomous agents with no human author or reviewer.
Why it matters
AWS finally ships its own LocalStack answer — and the story is the method: three teams of agents generate fidelity tests from Smithy models, run them against live AWS, and fix mismatches, with the full commit history and a public ledger of what does not work yet.
What you could build with it
A team shipping cloud infrastructure could point its AWS CLI, SDKs and coding agents at the local emulator to run integration tests in CI without cloud accounts or bills, catching API-shape errors before anything touches real AWS.
Does it hold up?
Immediately usable — RPM/Debian packages and Docker, plus an agent skill for setup — and it passed 2,100+ stars within a day of the announcement; AWS is explicit that it is for building and testing only, not production or security testing, since it does not evaluate IAM policies.
Built with AWS Emulator
- AWS's Official Emulator vs LocalStack: 160 Rust Crates, Fidelity Scores per Release, and a Telemetry DefaultDEV · Deep repo-level comparison with LocalStack covering architecture, fidelity disclosure, release cadence and the telemetry default.
- AWS launches AWS Emulatorblog · Concise launch summary: 400+ API models, CC0 licence, Linux packages and Docker, and the public list of known gaps.
- AWS Releases Local Emulator Written Entirely by Autonomous AI AgentsUnite.AI · Coverage of the launch, the agent-built origin story, and the limits including no IAM evaluation and 501s for unimplemented operations.
Learn more
First spotted on github: source.
More AI infrastructure
vLLM v0.34.0: extensible KV cache by default, Model Runner V2 only, and 10 new modelsThe open inference engine's latest release spans 1,061 commits from 412 contributors, adds 10 models including Mistral…infra · JEV 0.86llama.cpp v1.0.0: the local-AI engine's first stable releasellama.cpp and ggml hit v1.0.0, promising semantic versioning so breaking C API changes only arrive with major bumps.infra · JEV 0.84colibri: run 744B-parameter MoE models on consumer hardwarePure-C inference engine with zero dependencies that streams MoE experts from NVMe disk, keeping hot experts on GPU…infra · JEV 0.78claude-mem: persistent memory plugin that lets coding agents pick up where the last session left offPlugin that hooks five Claude Code lifecycle events, compresses session activity into a local SQLite + Chroma store…infra · JEV 0.74FreeToken: datacenter-scale MoE serving on desktop GPUsAn edge-native mixture-of-experts serving engine from UC Berkeley researchers that runs 290B+ parameter MoE models on…infra · JEV 0.74GBrain: Garry Tan's self-wiring memory layer for AI agentsY Combinator CEO Garry Tan's open-source, markdown-first knowledge layer that gives OpenClaw and Hermes agents…infra · JEV 0.71
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.