Updated
What makers build

AI code review & testing tech stack 2026: what 16 real products use

Reviewing pull requests, finding bugs and generating or running tests with AI.

Among the 16 products we track in AI code review & testing, the usual stack is OpenAI API (LLM API, 64%), Next.js (frontend framework, 78%) and Vercel (hosting, 67%): shares of the products that show each decision.

How they're built

The typical stack

The leading pick where at least 8 of them show the decision and the leader has at least a quarter of it.

DecisionMost common pickShareAt default usage
LLM APIOpenAI API7 of 11 · 64%$10/mo · GPT-6 Luna
Frontend FrameworkNext.js7 of 9 · 78%—
HostingVercel6 of 9 · 67%$40/mo · Pro + Flat Rate CDN 10M

Monthly bills add up to about $50 at the calculators' default usage, list prices. Set your own usage →

What they chose, decision by decision

Among the AI code review & testing that show each choice, from makers' products and open-source code alike. Under each tool, some of the products that chose it.

Small samples, fewer than 8 products: Authentication (Clerk 3, WorkOS 2) · Database (PostgreSQL 4, Supabase 2) · Product Analytics (PostHog 4, Amplitude 2) · Transactional Email (Resend 4, Nodemailer 2) · AI SDK & Agent Framework (LangChain 3, AI SDK 2) · LLM Observability & Evals (Helicone 2, Langfuse 1) · Payments (Stripe 4) · AI App Builders (v0 2, Lovable 1) · Backend Framework (NestJS 3, Express 1) · Database Access & ORMs (TypeORM 2, Drizzle ORM 1) · Error Monitoring (Sentry 3) · Open Model Hosting & GPUs (Fireworks AI 1, Baseten 1) · Vector Database (Qdrant 2, pgvector 1)

AI code review & testing we track

13 makers' products and 3 open-source projects, makers' products first, each with the tools it uses (the most common here first).

TragAI code review tool that checks every pull request against rules written in plain English. For teams that want to automate enforcement of their own code patterns.ClaudeLangChainQdrantWorkOS

Questions

What tech stack is behind AI code review & testing?

Among the 16 products we track in AI code review & testing, the usual stack is OpenAI API (LLM API, 64%), Next.js (frontend framework, 78%) and Vercel (hosting, 67%): shares of the products that show each decision.

How much does a typical AI code review & testing stack cost?

About $50 a month in bills at the pricing calculators' default usage and list prices. The biggest lines: Vercel $40 and OpenAI API $10.

Which products in AI code review & testing are open source?

3 of the 16 are open-source projects, known from their public code, among them costrict, packmind and agentic-qe.