Works withClaude CodeCodexCursorWindsurfCline

Ship production-grade apps, fast.

Open-source Next.js and Expo templates on AWS, built for your AI coding agent. Point it at a repo, describe an idea, and it ships a real, live app, with the infrastructure, auth, database, CI/CD, and security scanning already wired.

claude codeWeb
use github.com/elleskay/platform to
claude codeMobile
use github.com/elleskay/mobile-platform to

Spec-driven by default: your agent turns each brief into a spec, writes the code and the tests together, and CI blocks the deploy until every requirement is covered by a passing test.

100%
Spec coverage
9
Smoke checks
0
Stored keys
3
Live apps
2
Templates
MIT
License

Everything you need, already built.

Your agent inherits a complete Next.js and AWS production stack, so it spends its time on your product, not the plumbing.

Spec-driven gate

bound tests100% coverageblocks deploy

CI/CD pipeline

typechecklintcdk synth

Security scanning

CodeQLgitleaksnpm audit

OIDC deploys

short-lived roleno stored keysleast-privilege

Next.js on AWS

LambdaS3CloudFront

Post-deploy smoke test

healthheaders9 checks

Auth and database

Auth.js v5Neon PostgresJWT sessions

Observability

SentryPostHogready for a key

Validation

Zodevery server actiontyped boundaries

Eight technologies, already wired.

Across two templates, web (platform) and mobile (mobile-platform), configured and deploying on day one.

Next.jsWeb

App Router, SSR on Lambda via OpenNext.

ExpoMobile

React Native app, EAS build and OTA updates.

NestJSMobile

Typed API on Lambda and API Gateway.

AWS LambdaCloud

Serverless compute that scales to zero.

S3 + CloudFrontCloud

Static assets on a global CDN.

AWS CDKInfra

Infrastructure as code, one construct.

Neon PostgresData

Serverless Postgres with connection pooling.

GitHub ActionsCI/CD

OIDC deploys, no stored keys.

Prompt your idea. It does the rest.

You describe the app. The agent builds it, sets up your cloud once, and ships it to AWS.

1

Prompt your idea

Describe the app to your AI coding agent and point it at the template repo.

2

It scaffolds

The agent pulls from the template and writes the app, no boilerplate, no config.

3

It connects your cloud

On the first deploy it wires GitHub and AWS once: an OIDC role, a database, and secrets.

4

CI proves it

The spec gate hits 100%, security scans pass, and the smoke test confirms the deploy.

5

It ships

A live AWS URL, automatically, on every push from then on.

Real apps. Shipped.

Every one is live, on real auth and real data. Open any of them.

Showing 3 of 3
AI Tax Assistant Platform screenshot Live
AI · Tax

AI Tax Assistant Platform

A multi-tenant AI tax assistant platform for tax officers: each department gets its own workspace with a document-grounded assistant (RAG with clickable inline citations) and a visible step trace. One observed gateway routes every call across six OpenAI and Anthropic models by deterministic rules, logging latency, tokens, and cost, with cross-provider fallback. Officers compose their own lookup, template, and calculator tools (code runs in a QuickJS WASM sandbox), prompt versions activate only past an LLM-judge eval gate, and governance-as-code enforces PII redaction, a per-call cost ceiling, and a full audit trail.

DriveBuddy screenshot Live
AI · Mobility

DriveBuddy

AI driving companion for Singapore: an Expo app on a serverless NestJS API (Lambda + Neon Postgres). Surfaces live ERP, traffic, weather, and parking, tracks drives with background GPS and in-drive voice alerts for gantries and incidents ahead, itemizes fuel and ERP costs after every trip, and takes voice or text questions through a Claude assistant grounded in your vehicles and driving history.

CoverLens screenshot Live
AI · Insurance

CoverLens

AI insurance policy checker for Singapore. Drop in a policy PDF (read in your browser, never stored) and get a plain-language summary, a coverage breakdown, and a curated fine-print checklist. A LangGraph draft-verify-finalize loop grounds the model: deterministic code checks every quote against the document and re-drafts what fails, so nothing unquotable is shown.

Ready to ship production-grade apps, fast?

Point your agent at the platform repo and describe your first app. It builds, connects, and ships to a live AWS URL.

Open source, MIT Works with any coding agent Production-ready: spec gate + smoke test