AI Code Review for Next.js: what 10 makers' products chose
Among 10 makers' products built with Next.js that we know the AI code review of, cubic leads: 4 of them (40%). Next come Graphite (3) and CodeRabbit (1).
Dedicated reviewer, review platform, or the one bundled with tools you already pay for. A dedicated reviewer works on any major Git host and goes deepest on review itself; a review platform also changes how you open and merge pull requests (stacked PRs, merge queue); a bundled reviewer costs nothing extra if you already have a coding-assistant plan, but it is only as deep as that plan. An open-source reviewer you run yourself costs only the model calls, but the setup and tuning are yours.
What makers on Next.js chose
| Option | Next.js products | All makers |
|---|---|---|
| 4 (40%) | 26% | |
| 3 (30%) | 38% | |
| 1 (10%) | 26% | |
| 1 (10%) | 3% | |
| 1 (10%) | 6% |
Live makers' products with a source for both: that they're built with Next.js, and what they use for AI code review. A product using two options counts in both; not market share. "All makers" is the option's share among every maker's product that made this decision.
Which to pick, by situation
- Your repo is public and you want free reviews on every pull request
CodeRabbit 1 here
cubic 4 here - Your codebase is large and bugs come from how changes interact with other parts
Greptile 1 here - You open many small stacked pull requests on GitHub
Graphite 3 here
cubic
Dedicated AI reviewer4 Next.js products here (40%).
Best forGitHub pull request review with plain-English custom rules, plus scheduled scans of the whole codebase.
Trade-offGitHub only; paid per developer on private repos beyond a small free tier.
“It just performs the best. look at the benchmarks!!”
“It just performs the best. look at the benchmarks!!”
AI Code ReviewMaker says so · source ↗“Simply the best way to do code review.”
AI Code ReviewMaker says so · source ↗
Graphite
Review platform3 Next.js products here (30%).
Best forAI review together with stacked pull requests, a review inbox and a merge queue, for teams that open many small PRs.
Trade-offGitHub only; unlimited AI reviews start on the per-user Team plan, and stacking is a new workflow to learn.
“Knowledge graph framework on Neo4j for relationship intelligence, account context graphs, and temporal knowledge representation (planned deployment).”
“Knowledge graph framework on Neo4j for relationship intelligence, account context graphs, and temporal knowledge representation (planned deployment).”
AI Code ReviewMaker says so · source ↗“Our engineering team leans on Graphite Reviewer for pull request reviews. It doesn’t replace a human reviewer, but will catch a few things a week that our human reviewers miss. And the Graphite reviewer usually runs before a human reviewer gets to the pull request. Which is nice for saving expensive, human time. On an engineering team, for every hour of code writing, there are 10 hours of code fixing and maintenance. Graphite is pretty key for us to reducing that fixing and maintenance time. Another nifty thing about Graphite is pull request stacking. Our engineering team spans 14 timezones at Product Hunt. It’s not unusual for someone to crank out a bunch of work while the rest of the team is asleep. Pull request stacking is quite helpful for smoothing out that workflow.”
AI Code ReviewMaker says so · source ↗Also chosen, and not seen yet
Fewer Next.js products here: CodeRabbit (1), Greptile (1), Ellipsis (1).
Real options for AI code review not seen among these Next.js products yet: GitHub Copilot, PR-Agent, Cursor, Claude Code.
Getting AI code review right
Even solo, open pull requests instead of pushing straight to main, so the reviewer and CI run before code ships — this matters most when an AI agent wrote the code. Start with the free tier or the reviewer bundled with a plan you already have, write a short rules file about what matters in your codebase, and turn off comment categories you keep ignoring. Treat AI review as a first pass that catches the obvious, not a sign-off.
- Treating an AI approval as a sign-off and merging code, especially agent-written code, without reading the diff yourself.
- Leaving every comment category on, so the noise trains you to skim past the one comment that mattered.
- Switching a review workflow to run on pull requests from forks with secrets available, which hands your model key and write token to untrusted code.
The rest of the Next.js stack
What makers' Next.js products chose for their other decisions, the most common pick for each:
- Hosting: Vercel 1,078 of 1,312
- Transactional Email: Resend 493 of 830
- Database: Supabase 171 of 382
- Payments: Stripe 288 of 359
- LLM API: OpenAI API 222 of 301
- Authentication: Clerk 176 of 211
- Web Analytics: Google Analytics 105 of 197
- Product Analytics: PostHog 123 of 168
Questions
What do most Next.js apps use for AI code review?
Among 10 makers' products built with Next.js that we know the AI code review of, cubic leads: 4 of them (40%). Next come Graphite (3) and CodeRabbit (1).
How this is counted: a product is on Next.js when a live-product source says so (the maker, its website, a customer story or a subprocessor list), and the same for its AI code review. How evidence is collected.