Introduction

Gencow — Frontend + backend AI app framework for vibe coders

Gencow is a frontend + backend AI app framework for vibe coders who want to ship fast without compromising on quality. Build app screens and complete backend APIs with TypeScript — auth, database, realtime, file storage, AI, and cloud deployment — from one project.

Everything you need to ship a fullstack app:

  • Frontend-ready — Use Vite + React by default for new app screens and deploy them with your backend
  • Schema-first — Define your database with TypeScript (Drizzle ORM)
  • Instant APIs — createCrud() and typed procedure builders, with auto-generated client types
  • Built-in Auth — User management powered by better-auth (session-based, token-based)
  • Realtime — WebSocket push model — useQuery auto-refreshes on data changes
  • File Storage — private-by-default uploads, public asset URLs, and short-lived read grants
  • AI-Ready — Add AI, RAG, Memory, Tools with gencow add AI
  • Cron Jobs — Scheduled tasks with cron — interval, daily, weekly, cron
  • Cloud Deploy — gencow dev and you're live on https://<app>.gencow.app

Why Gencow?

Feature Gencow Supabase Firebase
Schema Drizzle (TypeScript) SQL (Console) NoSQL (Console)
API procedure + createCrud SQL / REST Firestore API
Auth Built-in (better-auth) Built-in Built-in
Realtime WebSocket push Realtime extension Firestore listeners
File Storage ctx.storage Storage Cloud Storage
AI Components gencow add AI Manual Vertex AI
Cron Jobs cron pg_cron Cloud Functions
Deploy gencow dev Dashboard firebase deploy
Self-host ✅ (Docker) ✅ ❌
Local Dev DB Cloud PostgreSQL PostgreSQL Emulators

Who is this for?

  • Vibe coders who use AI assistants (Cursor, Copilot, Claude) to build apps
  • Solo developers who want a full backend in minutes
  • Indie hackers who need auth + DB + AI + file storage without setup overhead
  • Agencies building prototypes and MVPs for clients

Tech Stack

Layer Technology
Runtime Bun
HTTP Server Hono
Database PostgreSQL (Gencow Cloud)
ORM Drizzle ORM
Auth better-auth (session-based + JWT)
Validation Zod + built-in v validator
Realtime Native WebSocket (push model)
AI Vercel AI SDK + Gencow proxy (Azure-first GPT-5.4 family with GPT-5 mini/nano compatibility)
Cloud Gencow Platform (gencow.app)

Architecture

Your App
├── gencow/                  ← Backend code (this is what you write)
│   ├── schema.ts            ← Starter tables; prefer `schema-*.ts` per domain as you grow
│   ├── schema-auth.ts       ← User-owned auth tables
│   ├── generated/           ← Server codegen (do not edit by hand)
│   │   ├── schema-auth.gen.ts ← Generated auth schema
│   │   └── db-schema.gen.ts   ← Aggregated schema for typed ctx.db
│   ├── auth.ts              ← Auth config (defineAuth)
│   ├── runtime.ts           ← Typed `procedure`, `httpRoute`, and `createCrud` bound to your schema + auth
│   ├── index.ts             ← Registers procedures & routes (`defineApi`)
│   ├── tasks.ts             ← Example: CRUD + custom procedures (optional)
│   ├── files.ts             ← Example: file upload/download logic (optional)
│   ├── seed.ts              ← Seed data (optional)
│   ├── README.md            ← Auto-generated AI guide
│   └── SECURITY.md          ← Security checklist
├── src/                     ← Vite + React frontend (recommended for new apps)
├── gencow.config.js         ← Project configuration
├── gencow.json              ← Cloud app ID (auto-created on deploy)
├── drizzle.config.ts        ← Database config (PostgreSQL)
└── package.json

tasks.ts and files.ts are starter examples from project templates — add your own procedure modules as needed; only index.ts (and the core gencow/ files) are required.

How it works:

  1. You define database tables in gencow/schema-*.ts files using Drizzle ORM — templates ship with schema.ts, but splitting tables across domain files (e.g. schema-tasks.ts) is preferred as the app grows
  2. You define procedures with createCrud() and procedure in gencow/*.ts, then register them in gencow/index.ts via defineApi
  3. gencow dev starts a Hono server with hot-reload and regenerates src/gencow/api.ts
  4. Your Vite + React frontend uses useQuery(api.tasks.list, {}) — data is reactive via WebSocket
  5. gencow dev ships everything to Gencow Cloud (PostgreSQL + isolated container)

Default frontend choice: When vibe-coding a new Gencow app, choose Vite + React. Use Next.js only when the user explicitly asks for Next.js/SSR or when adding Gencow to an existing Next.js project.

Next Steps

Installation