Create an AI Agent App

Create an AI agent app with Next.js, AI CLI workflow docs, MCP, skills, Better Auth, Drizzle, SQLite, Tailwind CSS, and shadcn/ui.

Updated 2026-05-21

ai-agentnextjsmcpai-cliskills

Use the AI Agent App pack when you want the application and the agent workflow to start together. It prepares a Next.js project plus AI CLI-oriented documentation and local agent tooling.

Starter pack

AI Agent App

AI docs, MCP, skills, and CLI workflow ready from day one

Open in builder

Scaffold command

bun create better-fullstack@latest my-ai-agent-app --ecosystem typescript --frontend next --css-framework tailwind --ui-library shadcn-ui --shadcn-base radix --shadcn-style nova --shadcn-icon-library lucide --shadcn-color-theme neutral --shadcn-base-color neutral --shadcn-font inter --shadcn-radius default --backend self --runtime none --api trpc --auth better-auth --payments none --email none --file-upload none --logging none --observability none --feature-flags none --realtime none --job-queue none --caching none --i18n none --search none --file-storage none --cms none --effect none --ai ai-cli --state-management none --forms react-hook-form --validation zod --testing vitest --animation none --database sqlite --orm drizzle --db-setup none --package-manager bun --git --web-deploy none --server-deploy none --install --addons biome ruler turborepo mcp skills --examples none --ai-docs claude-md agents-md cursorrules

Next.jsAI CLIMCPSkillsRelated docs

Generate the AI agent starter

Open the AI Agent App pack in the Stack Builder, or run:

bun create better-fullstack@latest my-ai-agent-app \
  --ecosystem typescript \
  --frontend next \
  --backend self \
  --database sqlite \
  --orm drizzle \
  --auth better-auth \
  --api trpc \
  --ai ai-cli \
  --addons biome ruler turborepo mcp skills \
  --ai-docs claude-md agents-md cursorrules

What the pack includes

Next.js for the product surface.
SQLite and Drizzle for local-first persistence.
Better Auth for accounts and sessions.
AI CLI setup, MCP support, skills, and generated agent docs.
Biome and Ruler so agent instructions and code quality live with the repo.

First things to customize

Define the user-facing agent job: research, coding, support, automation, or analysis.
Add the app data model the agent is allowed to read and write.
Tighten MCP/tool instructions before connecting external services.
Move from SQLite to a managed database when collaboration or production hosting needs it.

When this is the right pack

Choose this for AI-assisted developer tools, internal automation, agent dashboards, workflow copilots, or experiments where app structure and agent instructions should evolve together.

For the stack-level walkthrough, read Next.js AI CLI Agent Workbench.