> 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/docs/project-identity.md). # Project Identity This repository is **AI OS**. AI OS is the current canonical identity for the local-first operator cockpit built on the imported Claude OS dashboard foundation. It owns the host app shell, setup flow, local operator dashboard, local-agent telemetry, agents, memory, skills, activity, workspaces, share/settings surfaces, scheduler and Dream host jobs, runtime data loading, package/runtime metadata, privacy boundaries, and the compile-time extension platform. **Trend Finder** is the current registered extension inside AI OS. It owns the `trend-finder` extension ID, extension routes, public trend-source collectors, normalized evidence, topic clusters, score breakdowns, source health, provenance, creator angles, Creator Lens, watchlists, movement artifacts, Brief/demo surfaces, Engine Replay, and script-only historical backtest artifacts. The [public GitBook docs](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs) are the public reader-facing documentation for AI OS and Trend Finder. The repo-local docs remain the source of truth for implementation contracts, private runtime boundaries, setup details, and maintenance records. ## Ownership Boundaries * AI OS host data is local operator telemetry: setup state, tool detection, skills, memory, activity, workspaces, usage/spend, local-agent summaries, scheduler state, Dream output summaries, and generated runtime data. * Trend Finder data is public trend intelligence: source items, normalized evidence, source health, topic clusters, scores, creator angles, movement, watchlist state, run traces, and bounded backtest summaries. * Trend Finder creator-facing views are `/extensions/trend-finder/trends`, `/extensions/trend-finder/workbench`, `/extensions/trend-finder/hidden-gems`, `/extensions/trend-finder/sources`, `/extensions/trend-finder/watchlist`, and `/extensions/trend-finder/brief`. * `/extensions/trend-finder/engine` is a Trend Finder-scoped Engine Replay utility route. It is not a generic AI OS replay route and is not one of the six creator-facing extension views. * Trend Finder runtime data reaches the browser through `LiveData.extensions.items["trend-finder"]`. Host telemetry should not be described as Trend Finder evidence, and Trend Finder evidence should not be described as AI OS local telemetry. * Generated static HTML reports, hosted Trend Finder ingestion/scoring APIs, remote extension loading, and a dynamic extension marketplace are not implemented. ## Naming Rules * Use **AI OS** for the host app, shell, root README, package metadata, setup flow, share card, local operator cockpit, host routes, scheduler/Dream behavior, local-agent telemetry, host AI runtime docs, and general platform docs. * Use **ai-os** for package names, Worker names, logger prefixes, global runtime/cache prefixes, and new browser storage keys. * Use `AI_OS_*` for new script-only AI OS host runtime env vars where a host namespace exists. Do not add browser-exposed `VITE_AI_OS_*` aliases without a deliberate migration. * Use **Trend Finder** only for the extension, its UI/views, its collector, and docs that specifically describe public trend intelligence. * Use `trend-finder` for the stable extension ID, route segment, LiveData item key, and extension-local asset/cache/storage subkeys. * Use **Claude OS** only when describing inherited starter behavior or compatibility contracts. * Treat `findtrend` as a legacy hackathon-era name. Do not add new global `findtrend` identifiers. Existing `FINDTREND_*` env vars remain script-only compatibility names for the Trend Finder runtime and documented host-runtime fallbacks until a deliberate env migration happens. ## Compatibility Names Some names intentionally remain in place: * `VITE_CLAUDE_OS_*` is still the public setup/env namespace used by the inherited starter and current browser bundle. It covers setup wizard overrides, operator display fields, Dream setup preferences, and extension enablement. * `CLAUDE_OS_*` script-only names remain inherited scanner, anonymization, operator-photo, and local-path compatibility names where already implemented. * `AI_OS_*` is the canonical script-only namespace for host-owned runtime behavior where implemented, including host AI runtime and Dream activation. * `FINDTREND_*` is still the script-only compatibility namespace for the Trend Finder collector, Apify setup, OpenAI account-auth runtime, and documented host AI runtime fallback values. * `trend-finder` remains the stable extension ID and route segment. * New browser storage writes use `ai-os` keys. Legacy `claude-os` and `findtrend` storage-key prefixes are read and migrated to `ai-os` keys on access. Renaming those compatibility contracts should be handled as an explicit migration with aliases, docs, and tests. --- # 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/docs/project-identity.md?ask=&goal= ``` `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.