You outgrew v0, Lovable, or Bolt and need your own repo.
Builder preview works but production merge breaks role flows.
You want validated graph knowledge without abandoning your coding agent.
FAQ grouped v0, Lovable, and Bolt: you need one answer for the category.
Context
App builders converged in 2025-2026: prompt to full stack, often with database and auth scaffolding. They are excellent for proving demand. They are a different category from in-repo behavior skills. This umbrella page explains the category difference and links to v0 and Magic Patterns deep dives.
Common situations
Concrete cases from AI-shipping workflows. Each shows what the alternative handles and where validated graph knowledge and verification evidence help.
Lovable MVP validated, moving to custom monorepo
Situation
Lovable proved the idea. You rebuild on your Next.js monorepo with your auth and payments.
What App builders does
Hosted MVP generation and iteration on Lovable stack.
What Lamina adds
Portable validated graph knowledge and verify loop in the repo you will maintain for years.
Takeaway
Builders for validation; Lamina for behavior in owned code.
Bolt prototype with default auth flows
Situation
Bolt shipped a demo with generic user model. You need partner vs guest permissions Bolt did not model.
What App builders does
Fast deployed prototype on Bolt infrastructure.
What Lamina adds
Actor permissions and multi-role flows in GraphVersion before reimplementation.
Takeaway
Custom roles are where builders thin out.
Staying on builder platform for six-month pilot
Situation
Small team, no custom domain rules, acceptable vendor lock-in for now.
What App builders does
Continue on builder; optimize speed.
What Lamina adds
Defer until export or custom behavior is required.
Takeaway
Honest case to skip Lamina temporarily.
Comparison
Lamina vs app builders
Dimension
App builders
Lamina
Primary job
Generate apps from prompts on vendor stack
Spec behavior in your repo
Layer in stack
Generation platform
Transactional product graph + agent workflow
Primary output
Generated app or export bundle
Validated GraphVersion plus query projections
Writes app source?
Yes, platform-generated code
No
Behavior spec (states, flows, permissions)
Implicit in generated flows
Explicit GraphVersion
Durable in-repo artifact
Platform project
Validated GraphVersion plus query projections
Post-build verification
Platform preview
Independent Persona Missions with runtime evidence
They generate stack-locked apps. Lamina fits your existing repo and agent without replacing your stack.
We are migrating off a builder. When do we add Lamina?
Run /lamina-design on the first behavior-critical feature during migration, not after all tech debt is gone.
Is Lamina competing with app builders?
Category difference: generation platform vs in-repo behavior skill. Many teams use both sequentially.
Comparisons map stack layers, durable outputs, and provenance-marked legacy examples. Updated when major tools change positioning.
More comparisons
Install Lamina with your agent.
Copy the repository-matched prompt. Your agent installs the standalone CLI, adds every Lamina skill for your active agent, configures supported passive rules, checks the setup, and tells you when to start a fresh session with /lamina-init.
Skills work across coding agents. Passive setup currently supports Codex, Claude Code, and Cursor.
Cursor
Claude Code
Codex
Gemini
Pi
and more
Install manually on macOS/Linux4 shell commands
Run these in your project, then start a fresh agent session. On Windows, use the PowerShell installer in the copied agent prompt.
curl -fsSL https://github.com/aryaniyaps/lamina/releases/latest/download/install.sh | sh
npx skills add aryaniyaps/lamina --skill '*' -a <active-agent> -y