This article starts a series of notes on Gergely Orosz's What is Old is New Again talk that attempts to put his predictions (that strongly resonate with me) into practical steps for smart software engineers.
"Fullstack is in full swing"
When you start thinking about fullstack frameworks, you most probably think about the big three brothers: PHP's Laravel, Ruby on Rails and Python's Django.
Now narrow your scope down to JS/TS.
Anything?
If you ever heard of RedwoodJS, AdonisJS or NestJS, those might be the closest ones. But let's be honest, nobody is talking about them, few are using them, and they definitely didn't grow enough to be put on pair with the the big three.
And they still lack features we love and use every day (such as CLI, queues, (DB) models, and more) and/or ease of use/development/deployment, tests, community, etc.
Next.js?
Let's talk about Next.js, probably the most popular JS framework these days. Vercel (owner of Next.js) doesn't mention "fullstack" keyword anywhere on the visible side of the website, yet their meta descriptions says "the full-stack React framework for the web". I'd challenge their choice of words, but I am sure SEO comes to play here as well. In my definition, fullstack comes with a complete set of tools to cover development from end to end, yet Next.js doesn't care about DB communication/schema/migrations, authentication, authorization, and so much more. Recent merge of Remix (main competitor) with React Router just shows the harsh truth - that these frameworks are just a router on steroids.
The Javascript way
Then there is The T3 Stack, a mere collection of libraries that got more stars than two our of three JS fullstack libraries mentioned above!
And with recent trends being just about "moving to the server" (State of JS 2023 conclusion from Theo Browne, T3 Stack creator), we are clearly far from fullstack.
Action points
So my predictions are:
- Fullstack era will indeed come.
- NestJS won't become popular enough, and thus JS will miss this round of fullstack frameworks prevalence.
- Companies will use the big three or a combination of TS libraries (T3 Stack or similar) to stay one-lang.
- Knowing TypeScript is a must.
- In order to remain relevant in the job market, we need to be fluent with at least one of the big three.
My personal action point is to learn Django. I have past (working) experience with Laravel, some (university) experience with Rails, but I never touched Django, and barely worked with Python. Time to change that!
Bonus: An interesting approach
What I appreciate seeing in recent years is the attempt to form fullstack JS/TS framework from different angle, and that is from frontend to backend (opposite of where all the big three came from). I can see the trend all over the place, with Partial Prerendering in Next.js, to Astro Islands, to Streaming in SvelteKit. All the big three struggle with frontend interactivity, because they need JS to serve that purpose. What if we solved interactivity first, and then added all the boring (but mandatory) tools to JS frameworks later? Only time will tell if this seemingly weird approach bears fruit.
Stay tuned for the second note in which I will discuss how product/business-minded will get (un)fair advantage in their next job hunt.
Top comments (0)