By Jake Mcdonald, founder of ShipEmber · November 2, 2026 · About an 11-minute read · Free kits checked against their GitHub repos today
I'm Jake Mcdonald. I sell a paid Next.js starter (ShipEmber), so this page has a conflict of interest. I'm still going to say this clearly: free open-source starters are often the right first move. The question is what "free" actually includes — and what you still have to wire yourself before the first paid customer.
I verified the free options below against their public repos or sites on November 2, 2026. Paid prices match each vendor's live page the same day (or our own pricing for ShipEmber).
Free vs paid at a glance
| Kit | Price | Auth | Stripe subscriptions | Best for |
|---|---|---|---|---|
| nextjs/saas-starter | Free (MIT) | Email/password + JWT cookies | Checkout + Customer Portal (basic) | Learning the shape of a SaaS |
| create-t3-app | Free (MIT) | Auth.js optional | No — bring your own | Typesafe scaffold, not a SaaS kit |
| ixartz/SaaS-Boilerplate | Free (MIT) | Clerk | Not the focus of the public README | Multi-tenant + i18n learning |
| ShipEmber | $49 launch week, then $79 | Auth.js v5 (Google, GitHub, magic links) | Checkout, portal, signed idempotent webhooks | Minimal solo Free→Pro MVP |
| ShipFast / Makerkit / etc. | ~$157–$1,499 | Varies | Usually yes | Broader indie or B2B surface |
What "free" actually means
Free usually means MIT code you can clone. It does not mean:
- OAuth providers configured for production,
- webhook idempotency and plan gating you can trust under retries,
- marketing pages ready to rebrand,
- or someone answering Discord questions when Stripe returns a weird event.
You still pay with time. Sometimes that trade is correct.
nextjs/saas-starter (Vercel / Next.js)
Verified: github.com/nextjs/saas-starter — MIT, ~16k stars when I checked today. Demo linked from the README: next-saas-start.vercel.app.
From the README, you get:
- Next.js + Postgres + Drizzle + Stripe + shadcn/ui
- Marketing landing page and a pricing page wired to Stripe Checkout
- Dashboard CRUD, basic Owner/Member RBAC
- Stripe Customer Portal for subscription management
- Email/password auth with JWTs in cookies
- Middleware to protect logged-in routes; activity logging
Honest take: This is the best free reference I know for "what a clean Next.js + Stripe + Postgres app looks like." Gaps vs a commercial kit: no Google/GitHub OAuth out of the box, no polished one-file rebrand, and you will harden webhook/idempotency patterns yourself for production. Start here if you're learning. Graduate when the missing pieces cost more evenings than a cheap paid kit.
create-t3-app
Verified: create.t3.gg and the t3-oss/create-t3-app repo (MIT). Install with npm create t3-app@latest.
Their own copy is clear: it is not an all-inclusive SaaS template. It scaffolds the pieces you opt into — Next.js, TypeScript, Tailwind, Prisma (or others), tRPC, and Auth.js (NextAuth) — with strong opinions about type safety. No Stripe. No pricing page. No customer portal.
Honest take: Perfect when you want a typesafe app shell and you intend to own billing. Terrible if you expected "clone and charge cards tomorrow." Pair it with Stripe docs (or a kit) when you need subscriptions.
ixartz/SaaS-Boilerplate
Verified: github.com/ixartz/SaaS-Boilerplate — MIT, demo at react-saas.com. README lists Next.js, Tailwind, shadcn/ui, Clerk auth, multi-tenancy with teams/roles, Drizzle, i18n, landing, dashboard, tests, and CI. Stripe is not the headline feature of the public README.
Honest take: Useful if you want to study multi-tenant patterns and you're fine with Clerk (their free tier has limits; paid Clerk is a separate bill). If your requirement is "Auth.js + Stripe subscriptions on Postgres with no third-party auth vendor," this is the wrong free kit.
When free is the better pick
- You're learning App Router, Drizzle/Prisma, or Stripe for the first time.
- You have a weekend and a high tolerance for wiring env vars and webhook secrets yourself.
- Your product is not ready to charge anyone — scaffolding beats buying.
- You specifically want create-t3-app's typesafe stack and will add billing later.
Related reading on that tradeoff: topic #12 in our internal notes became this page. Also see Best Next.js SaaS boilerplates in 2026.
When a paid kit is the better pick
- You've already burned a week on auth + webhooks and just want the boring path paved.
- You need OAuth (Google/GitHub) + magic links + Stripe Checkout + portal + server-side Free/Pro gating together.
- You want a small, opinionated codebase with docs aimed at shipping, not at teaching every option.
- Your hourly rate makes $79–$249 cheaper than two more evenings of billing bugs.
Paid kits are not equal. ShipFast, Makerkit, and supastarter buy you more surface area (and more learning). ShipEmber buys you the core loop only. I wrote separate comparisons: ShipFast, Makerkit, supastarter, Shipped.club.
Why choose ShipEmber (if you buy anything)
Here's the honest pitch — same points I'd tell a friend.
1. Paid for the gap free kits leave
ShipEmber is Auth.js v5 + Stripe subscriptions (Checkout, customer portal, signature-verified idempotent webhooks) + Prisma/Postgres + a gated dashboard + marketing pages + one-file rebrand. That's the gap between "I cloned saas-starter" and "I can charge Pro tonight."
2. Price stays near free-kit territory
Live price: $49 launch week, then $79 — see pricing. One-time. Instant zip download. 14-day refund if it doesn't work as described. Lifetime updates to v1.
3. Intentionally small
No orgs, no i18n, no five payment providers. If you need those, buy Makerkit or supastarter — or start from nextjs/saas-starter and grow into them.
If you want the paid core loop
Get the zip, add your keys, and build the product part.
Pricing details · What's inside · Auth.js + Stripe checklist
Related: Full boilerplate comparison · Stripe subscriptions deep dive · Why I built ShipEmber
Verification note: nextjs/saas-starter and ixartz/SaaS-Boilerplate READMEs and licenses checked on GitHub on November 2, 2026. create-t3.gg checked the same day. Vendor pages and READMEs change.
— Jake Mcdonald, Springfield, IL
Top comments (0)