Show HN: Boot a tiny app-making OS inside an AI chat
BlueBookOS is a tiny operating system that you paste into an AI chat to help build apps. It uses a source-first approach with the RAu language as the artifact contract, producing standalone HTML5 applications. No server or build tools required.
Live Sandbox / REPL
Try BlueBookOS in ChatGPT.
Open the GPT that runs this page’s BlueBookOS microkernel, then ask it to build a source-first RAu artifact in a live chat sandbox.
Launch Sandbox / REPL
Open source signal
Star BlueBookOS on GitHub.
If this project helped you build faster, star the repo so other builders can find it. The count below updates live from GitHub when the page is online.
Repo: Machine-Publishers/BlueBookOS ★ Loading stars… ⑂ Loading forks…
★ Star on GitHub
Two installation options
Pick your paste.
Two installation options. Both buttons copy a complete BlueBookOS boot packet. Pick the version that best matches the AI model you're using.
What is this See what it can make
Jailbreak More permissive boot packet for models that accept it.
Safe Compatibility-focused boot packet for stricter chats.
Showing Safe · compatibility-focused boot packet.
Loading selected copy-pasta…
A tiny OS for making apps with AI
BlueBookOS boots in your chat.
BlueBookOS is a small set of rules and source code you paste into another AI chat. It helps that chat build apps carefully: first the RAu contract, then the working file. RAu is the little instruction language inside it. You can start without knowing either one.
Install it See the demo
1Demo included
—Source lines
—Built lines
0Installs needed
RAu is used here as a source-first artifact contract. The HTML5 files are host ports that render the behavior described by the RAu source. This app is intentionally plain to operate: open it, open the demo, inspect the final RAu, inspect the final HTML, and run the rendered page in place.
The main product claim is simple: a good AI artifact should not only be impressive to view; it should be reusable, reviewable, copyable, and portable into the next project.
The key words MUST, SHOULD, and MAY are used in their everyday standards-document sense: MUST means required for this showcase pattern, SHOULD means recommended for most projects, and MAY means optional but supported.
This file is self-contained. It does not require a server, package manager, build pipeline, remote stylesheet, CDN, or network call.
RAu
The programming language and runtime used as the semantic source contract for an artifact.
Artifact
A complete app, game, editor, reader, visualizer, or workflow unit intended to be shipped or remixed.
Host Port
The executable target implementation. In this package, every host port is standalone HTML5.
Rendered Page
The live browser view generated by loading the final HTML port into an embedded frame.
Source-First
The RAu contract is treated as the durable product definition before host-language changes are made.
Vibe Coding
A fast builder workflow where a human steers a frontier model with complete artifacts, clear goals, and acceptance criteria.
The package MUST embed the demo locally. No runtime fetch is required to inspect source or render the included pages.
The demo MUST expose final RAu. The RAu view is the artifact contract a model or human can reason about before changing the host implementation.
The demo MUST expose final HTML5. The HTML view is the copyable, shippable browser port derived from the source-first artifact.
Each example MUST render inside the app. The rendered page view makes the spec demonstrable without leaving the document.
The app SHOULD be usable as a model prompt payload. A builder should be able to paste this entire file into a frontier model and ask for a new artifact, a refactor, a port, or a new catalog entry.
The app MAY be extended with new examples. Additional RAu/HTML pairs can follow the same pattern: source contract, host port, metadata, rendered preview.
The reference flow is intentionally lightweight. It works for games, editors, readers, canvas tools, dashboards, simulations, and other UI-heavy artifacts.
1State the intent
Name the artifact, user controls, data model, render targets, and success conditions.
2Write the RAu
Use RAu as the product contract for behavior, guards, events, and rendering.
3Derive HTML5
Generate a standalone browser port with complete input and render behavior.
4Ship and remix
Run the page, copy the source, modify the contract, and reuse the pattern.
Loading…
Preparing embedded artifacts.
The live rendered page is running from embedded srcdoc.
Recommended workflow: copy the large prompt at the top, replace the bracketed goal with the app you want, and ask the model to return the RAu contract before the standalone HTML5 file. Use the examples below as references for how the source-first pattern should look.
Start with the prompt.
Do not rely on screenshots. The useful pattern is the source-first contract followed by a working standalone host port.
Give one concrete target.
Examples: “make a calendar app,” “derive a puzzle game,” “port this into a todo tool,” or “add a fifth example.”
Ask for RAu first, then HTML5.
Preserve the source-first rule: update or derive the RAu contract before changing the host port.
Demand a standalone output.
Require a single HTML5 file with no build step, no CDN, and no runtime network dependency unless explicitly intended.
Use acceptance checks.
Ask the model to list controls, expected behaviors, edge cases, and what changed from the original examples.
Best for
Rapid prototypes, client demos, internal tools, interactive specs, game mechanics, UI experiments, and product pitches.
Model input
The full HTML file plus a clear instruction: extract the RAu/HTML pattern and generate the next artifact.
Model output
A revised RAu contract and a complete standalone HTML5 app, ready to save as a local file and run.
Branding is intact.
The artifact is clearly branded as BlueBookOS: Thee GPT Microkernel™ and Powered by RAu.
RAu is visible.
The final RAu source can be inspected and copied without a build step.
HTML5 is visible.
The final standalone host port can be inspected, copied, downloaded, and opened.
Rendered page works locally.
The preview runs with local embedded source and does not depend on remote assets.
Future builders can reuse it.
The package includes enough context for a human or model to derive another artifact from the pattern.