{"slug": "my-friend-s-group-chat-just-got-roasted", "title": "My friend's group chat just got roasted", "summary": "A developer published Kudos AI, a free demo that turns a group-chat JSON export into roasty friend awards and an AI-generated awards ceremony video that users can post back into the chat. The monorepo uses pnpm workspaces with a Next.js 15 web app, a BullMQ worker, and packages for chat ingestion and awards, backed by Postgres 16 and Redis 7 via docker-compose; subjective award judging runs through the Jev/TypeSafe API and ceremony rendering through Magic Hour with async webhooks. Users pick a gentle, medium or spicy roast level, and the demo accepts native Kudos JSON or auto-detected Telegram, Messenger and Discord exports, validating for size, structure and malicious content before normalizing messages and computing stats.", "body_md": "Turn a group-chat JSON export into roasty friend awards and an AI-generated awards ceremony you can drop back into the chat.\n\n**Free demo.** Product docs are in [`/docs`](https://github.com/defAaron/gc-wrapped/blob/main/docs). Local dev uses the slideshow ceremony unless Magic Hour credentials are set.\n\n1. User uploads a **JSON** chat file (native[Kudos format](https://github.com/defAaron/gc-wrapped/blob/main/docs/02-user-flows.md#kudos-chat-json-v1) or auto-detected platform export).\n2. We **validate** for size/structure/malicious content, normalize messages, compute stats, and use[Jev](https://jevtypesafeai.com/jev/api) for subjective award judging.\n3. User picks roast level (**gentle / medium / spicy** ) and optional avatars.\n4. [Magic Hour](https://docs.magichour.ai/integration/overview) renders a shareable ceremony video (async + webhooks).\n5. User gets a link and/or MP4 to post in the group.\n\n**Monorepo** (`pnpm` workspaces):\n\n| Path | Role | \n|---|---|\n| `apps/web` | Next.js 15 app (UI + Route Handlers API) | \n| `apps/worker` | BullMQ worker (analyze + ceremony jobs) | \n| `packages/chat-json` | JSON ingest, adapters, validation | \n| `packages/awards` | Stats, deterministic awards, Jev orchestration | \n| `packages/shared` | Shared types/utilities | \n\n**Local dependencies:** Postgres 16 and Redis 7 via [`docker-compose.yml`](https://github.com/defAaron/gc-wrapped/blob/main/docker-compose.yml).\n\n**Environment:** copy [`.env.example`](https://github.com/defAaron/gc-wrapped/blob/main/.env.example) to `.env` at the repo root (the web app loads it from there).\n\n| Variable | Default / notes | \n|---|---|\n| `DATABASE_URL` | `postgres://kudos:kudos@localhost:5432/kudos` | \n| `REDIS_URL` | `redis://localhost:6379` | \n| `OBJECT_STORE` | `local` (default) or`r2` | \n| `OBJECT_STORE_DIR` | `.data` when`OBJECT_STORE=local` | \n| `APP_ORIGIN` | Extra CSRF origins, comma-separated (the request host is always allowed) | \n| `R2_ACCOUNT_ID` ,`R2_ACCESS_KEY_ID` ,`R2_SECRET_ACCESS_KEY` ,`R2_BUCKET` | Required when `OBJECT_STORE=r2` | \n| `SESSION_SECRET` | Required for signed session cookies | \n| `TYPESAFE_API_KEY` | Jev / TypeSafe API (analyze) | \n| `MAGIC_HOUR_API_KEY` | Ceremony render | \n| `MAGIC_HOUR_WEBHOOK_SECRET` | Magic Hour webhook verification | \n\n**Prerequisites:** Node 22, [pnpm](https://pnpm.io/) 9, Docker (for Postgres + Redis).\n\n```\npnpm install\ncp .env.example .env   # fill secrets as needed\ndocker compose up -d\npnpm --filter @kudos/web db:push\n```\n\n**Web (dev):**\n\n```\npnpm dev\n# or: pnpm --filter @kudos/web dev\n```\n\n**Worker (dev, separate terminal):**\n\n```\npnpm --filter @kudos/worker dev\n```\n\nSchema is managed with [Drizzle](https://orm.drizzle.team/) (`apps/web/src/db/schema.ts`). For local/dev, apply the current schema to Postgres:\n\n```\npnpm --filter @kudos/web db:push\n```\n\nUses `DATABASE_URL` from the root `.env` (see `apps/web/drizzle.config.ts`). Do not commit `.env`.\n\nProduction build for the Next.js app:\n\n```\npnpm --filter @kudos/web build\n```\n\nFrom the repo root:\n\n```\npnpm test          # vitest in all workspaces\npnpm typecheck     # tsc --noEmit in all workspaces\npnpm secrets:scan  # gitleaks (matches CI)\n```\n\nCI runs `test`, `typecheck`, and `secrets:scan` on push/PR ([`.github/workflows/ci.yml`](https://github.com/defAaron/gc-wrapped/blob/main/.github/workflows/ci.yml)).\n\n| Doc | Contents | \n|---|---|\n| [01-product-brief.md](https://github.com/defAaron/gc-wrapped/blob/main/docs/01-product-brief.md) | What Kudos AI is and what the demo includes | \n| [02-user-flows.md](https://github.com/defAaron/gc-wrapped/blob/main/docs/02-user-flows.md) | Export guides, upload, awards, and sharing | \n| [03-awards-system.md](https://github.com/defAaron/gc-wrapped/blob/main/docs/03-awards-system.md) | Award catalog, roast levels, and how winners are chosen | \n| [04-data-and-privacy.md](https://github.com/defAaron/gc-wrapped/blob/main/docs/04-data-and-privacy.md) | Consent, retention, and third parties | \n\n| Area | Choice | \n|---|---|\n| **Ingestion** | `.json` upload only at demo MVP; adapters for Telegram / Messenger / Discord JSON | \n| **Jev** | TypeSafe direct `POST https://api.typesafe.ai/v1/systemone` (pinned model); gateway optional for dev | \n| **Ceremony** | Magic Hour async APIs ( `text-to-video` ,`ai-talking-photo` , TTS) | \n| **Pricing** | Free for demo | \n| **Roast dial** | Gentle / medium / spicy | \n| **Fairness** | Max **4** awards per person | \n\n```\n/docs/                 Product guides\n/apps/web/             Next.js UI + API routes\n/apps/worker/          Background jobs (BullMQ)\n/packages/chat-json/   Schema, validators, platform adapters\n/packages/awards/      Stats + Jev orchestration\n/packages/shared/      Shared types\n/packages/storage/     Local disk and R2 object storage\n/fixtures/             Sample & malicious JSON for tests\n```\n\nTBD.", "url": "https://wpnews.pro/news/my-friend-s-group-chat-just-got-roasted", "canonical_source": "https://github.com/defAaron/gc-wrapped", "published_at": "2026-11-20 23:07:22+00:00", "updated_at": "2026-11-20 23:44:06.390025+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "ai-products", "ai-tools", "developer-tools"], "entities": ["Kudos AI", "Jev", "TypeSafe", "Magic Hour", "Next.js 15", "BullMQ", "Postgres 16", "Redis 7"], "also_reported_by": [], "takeaway": "Kudos AI's demo pipeline validates and normalizes chat JSON, computes stats, sends subjective award judging to the Jev/TypeSafe API, and renders ceremony video asynchronously through Magic Hour webhooks, with Postgres 16 and Redis 7 run locally via docker-compose.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/my-friend-s-group-chat-just-got-roasted", "markdown": "https://wpnews.pro/news/my-friend-s-group-chat-just-got-roasted.md", "text": "https://wpnews.pro/news/my-friend-s-group-chat-just-got-roasted.txt", "jsonld": "https://wpnews.pro/news/my-friend-s-group-chat-just-got-roasted.jsonld"}}