vinext was born from an experiment in pushing AI to its limits. Almost every line of code in this repo was written by AI, and every pull request is both created and reviewed by AI agents. We welcome human contributions, but if you want to have a good time in this repo, you’re going to want to use AI.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/cloudflare/vinext/llms.txt
Use this file to discover all available pages before exploring further.
Recommended setup
We use OpenCode with Claude Opus 4.6, set to max thinking. This is the same setup that built the project.Before you open a PR
Before opening a pull request, ensure you:- Run the test suite.
pnpm testruns Vitest.pnpm run test:e2eruns Playwright. - Add tests for new functionality. Unit tests go in
tests/*.test.ts. Browser-level tests go intests/e2e/. - Run the linter and type checker.
pnpm run lint(oxlint) andpnpm run typecheck(tsgo). - Read
AGENTS.md. It has the architecture context, key gotchas, and development workflow that will save you (and your AI) time.
AI code review
When you open a PR, tag one of our AI reviewers in a comment:/bonk— AI code review using Claude Opus 4.6/bigbonk— Same model, max thinking mode. Use this for complex or large PRs.
Debugging
For browser-level debugging (verifying rendered output, client-side navigation, hydration behavior), we recommend agent-browser. Unit tests miss a lot of subtle browser issues. agent-browser has been effective at catching them throughout this project.What to work on
Check the open issues. Issues labeledpost-launch are known gaps we’re planning to address. If you’re looking to contribute, those are a good place to start.
Project structure
See the Development Setup guide for the full project structure, key files, and architecture patterns.Reporting bugs
If something doesn’t work with your Next.js app, please file an issue — we want to hear about it. Before you do, try pointing an AI agent at the problem. Open your project with Claude Code, Cursor, OpenCode, or whatever you use, and ask it to figure out why your app isn’t working with vinext. In our experience, agents are very good at tracing through the vinext source, identifying the gap or bug, and often producing a fix or at least a clear diagnosis. An issue that includes “here’s what the agent found” is significantly more actionable than “it doesn’t work.” Even a partial diagnosis helps — stack traces, whichnext/* import is involved, whether it’s a dev or production build issue, App Router vs Pages Router. The more context, the faster we can fix it.