This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Turn a one-sentence spec into a coherent Rails 8.1 API + native SwiftUI iOS + native Jetpack Compose Android implementation — renamed end-to-end, validated across three layers, in under an hour. A Claude Code agent. Free, MIT. CLI, MCP server, or plugin.
Hey Product Hunt 👋
The pain I keep hitting: anyone shipping a mobile product has to implement the **same domain three times** — multi-tenant Rails API, native iOS, native Android — and keeping them coherent under iteration is where weeks vanish. Most "AI builds an app" tools stop at a single web frontend.
`nativeapptemplate-agent` is my answer. Tell it one English sentence — e.g. "a walk-in queue for a barbershop" — and it produces three coherent, buildable, validated projects: a Rails 8.1 API + native SwiftUI iOS app + native Jetpack Compose Android app. Renamed end-to-end. No contract drift. Structural + runtime + vision-judge validation built in.
A few non-obvious things:
▸ Three distribution surfaces from one codebase — standalone CLI (npx), an MCP server (Cursor / Cline / Goose / any MCP-capable assistant), and a Claude Code plugin (/generate-app + /walk-app slash commands, including a UI walk on the simulator via mobile-mcp).
▸ Validated 12/12 end-to-end — three demo specs × two editions × two platforms, all passing structural + runtime + Opus-4.7 vision judge on a real iPhone 17 Pro simulator and Android emulator. Not mocks.
▸ Built on a production boilerplate — the agent customizes NativeAppTemplate (https://nativeapptemplate.com), the three-platform template I extracted from a queue-management app that's been live on both app stores for ~2 years. API + free-edition mobile clients are MIT; paid SKUs add multi-tenancy, invitations, role permissions.
Built solo in Tokyo, powered by Claude Opus 4.7 + the Claude Agent SDK. Code, validation reports, and the planner / three-workers / reviewer / judge architecture are all on GitHub (MIT).
Would love feedback on:
- the planner → three-workers → reviewer → vision-judge architecture
- whether the three-surface distribution (CLI / MCP / plugin) feels useful in your editor
- what "simple-CRUD SaaS" specs you'd try first
Happy to answer anything in the comments — replying live throughout the day.
NativeAppTemplate Agent was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #150 on the daily leaderboard. Turn a one-sentence spec into a coherent Rails 8.1 API + native SwiftUI iOS + native Jetpack Compose Android implementation — renamed end-to-end, validated across three layers, in under an hour. A Claude Code agent. Free, MIT. CLI, MCP server, or plugin.
NativeAppTemplate Agent was featured in Open Source (68.5k followers), Developer Tools (513.4k followers), Artificial Intelligence (469.9k followers) and GitHub (41.2k followers) on Product Hunt. Together, these topics include over 201.8k products, making this a competitive space to launch in.
Who hunted NativeAppTemplate Agent?
NativeAppTemplate Agent was hunted by Daisuke Adachi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how NativeAppTemplate Agent stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Daisuke Adachi