> For the complete documentation index, see [llms.txt](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/demo.md).

# AI OS Demo

## System Summary

AI OS is a local-first operator cockpit for AI work. It combines local telemetry, memory, skills, setup, agent surfaces, and a compile-time extension platform in one React/TanStack/Vite application.

The current build presents AI OS as the host dashboard while keeping extension products scoped to their own routes. Trend Finder is the movement-analysis extension for AI creators, and AI Rogue is the opt-in local roguelike extension that turns browser-safe AI OS activity into capped local progression.

## Core Stack

* React 19, TanStack Router/Start, Vite, Tailwind CSS 4, and TypeScript.
* Bun for local scripts, setup, aggregation, scheduler jobs, tests, and builds.
* React Query for runtime data loading.
* Cloudflare Worker SSR for the full app deployment path.
* Cloudflare Pages for the separate static public demo path.
* Vitest, Playwright, ESLint, Prettier, bundle-budget checks, and private artifact guards for release validation.

## Main Product Surfaces

* Home dashboard for local operator status, usage, source readiness, and activity summaries.
* Skills, memory, activity, workspaces, setup, share, and settings routes.
* Agent routes for Hermes, Claude Code, and OpenClaw.
* Knowledge Graph route with committed seed graph fallback and optional local project graph ingest.
* Trend Finder extension routes for Trends, Workbench, Hidden Gems, Sources, Watchlist, Brief, and Engine Replay.
* AI Rogue extension routes for Play, Ledger, Loadout, and Settings.

## Data Flow

AI OS keeps local operator data separate from public demo data.

Local development uses Vite middleware and `src/data/live-data.json` to serve runtime data to the browser. The aggregate and scheduler scripts can refresh that generated data from local machine signals, reviewed sources, and enabled extension jobs.

The Cloudflare Pages demo uses committed browser-safe fixtures under the demo website boundary and builds static output into `demo-website/dist`. That path does not run local bridge endpoints, hosted collectors, schedulers, account auth flows, uploads, admin mutations, server storage, or private telemetry reads.

## Privacy And Safety Boundary

The system treats private local state as operator-only data. Local bridges are loopback-only, and sensitive reads or admin actions are token-gated during development. Browser-facing payloads are sanitized before they are shown in the dashboard or written into public demo fixtures.

Secrets should stay in ignored local files or deployment secrets. The Cloudflare API token and Cloudflare account ID are configured in `.env.local` for local Wrangler and Cloudflare API operations. The token value is not included in this document and should not be committed. `.env.local.example` contains placeholder names for new checkouts.

## Demo Paths

For a local UI demo:

```bash
bun install
bun run dev
```

For a static Cloudflare Pages preview:

```bash
bun install
bun run demo:preview:pages
```

For a Worker SSR preview:

```bash
bun install
bun run worker:preview
```

## Demo Narrative

Start with AI OS as the local cockpit: show the home dashboard, source readiness, and agent surfaces. Then move into Trend Finder to show ranked topics, evidence labels, scoring breakdowns, hidden gems, watchlist entries, source health, and the Brief handoff. Use Engine Replay as the proof surface for the latest sanitized run state. If AI Rogue is enabled, show how local browser-safe activity feeds capped progression without exposing private telemetry.

When presenting the public demo, describe it as a static browser-safe demo powered by committed fixtures. Do not describe fixture data as live collection, live AI clustering, or hosted source execution unless the current environment is actually running those credentialed paths.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/demo.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.