wasp VS aider

We used Wasp’s built-in auth which makes your auth totally yours and independent of any 3rd party service. Under the hood, it uses Lucia and Arctic to give you email, username and multiple OAuth providers out of the box.

Wasp (https://github.com/wasp-lang/wasp) has actually worked out quite well! It just crossed 10k stars on GitHub and is currently the fastest-growing full-stack framework for React & Node.js. It's being used in both startups and enterprises.

Although Wasp has its own DSL/compiler, the secret to its adoption is probably that it works with the existing stack, like React & Node.js. From the developer's perspective, it feels like a framework; the "compiler" part is just what gives it its superpowers.

Another example of a React framework utilizing Vite to give their users a SPA experience is Wasp - a full-stack framework for React & Node.js that drastically cuts the boilerplate. Despite being a full-stack framework, it focuses on the standardized approach of deploying a client-side React app with a Node.js server to be as portable as possible. With this approach, you can deploy your app pretty much anywhere, as well as self-host it, which is also a thing that we mentioned before in this article.

As before, you will be redirected to the application's login page. Click to link to sign up to create a new account. After authenticating, you will be able to access the todo list functionality as before. ## Conclusion In this guide, we demonstrated how to build and deploy a Wasp application to Koyeb. We started with one of Wasp's templates to create a working, full-stack web application backed by a database. We migrated the application's configuration from a local SQLite database to an external PostgreSQL database to prepare for deployment. Afterwards, we created a multi-stage `Dockerfile` to build and configure our various application layers. Finally, we deployed the backend and web app to Koyeb by targeting different stages in the `Dockerfile`. This tutorial covers the basics of how to manage a Wasp project and deploy to a production environment. As you continue to develop your projects, be sure to check out the [Wasp documentation](https://wasp-lang.dev/docs) to learn how to integrate new features, work with the data model, and leverage the development framework to make your life easier.

First off, Wasp is a full-stack React, NodeJS, and Prisma framework with superpowers. It just crossed 10,000 stars on GitHub, and it has been used to create over 50,000 projects.

When building AI Blog Articles, I decided to get started as fast as possible. So I looked for a free boilerplate and stumbled upon Open SaaS, which used YC-backed Wasp. It is a full-stack React + NodeJS + Prisma that takes 8 hours to get started with.

Exactly. Wasp, https://wasp-lang.dev, is the only framework in the React/Node/Prisma space that's taking this opinionated approach to full-stack development.

For example, you get full-stack auth by just adding this to your config file:

`auth.methods: { email: {}, google: {} }`

Then you on-the-fly Auth UI components and all the necessary hooks

If you already have some sort of foundation in programming, use AI and some great abstractions/frameworks to get things done even faster. For example, instead of creating everything from the ground up (and probably suffering on little things along the way) you can skip repeating yourself a ton of times by using Wasp, which is a great React/Node full-stack framework that takes care of managing the boilerplate side of programming for you. 🤯

Aider is one of my favorite AI agents, especially because it can work with existing codebases. We've seen a lot of good results from folks who used it with Wasp (https://github.com/wasp-lang/wasp) - a full-stack web framework I'm working on.

A "marketingy" demo video: https://www.youtube.com/watch?v=DXunbNBpgZg&ab_channel=Wasp

My open source tool aider [0] has long offered a "AI pair programming" workflow. Aider's UX is similar but not identical to Copilot Workspaces.

Aider is more of a collaborative chat, where you work with the LLM interactively asking for a sequence of changes to your git repo. The changes can be non-trivial, modifying a group of files in a coordinated way. So much more than just the original copilot "autocomplete".

Workspaces seems more agentic, a bit like Devin. You need to do a bunch of up-front work to (fully) specify the requirements. Then the agent goes off and (hopefully) builds what you want. You need to fully understand what you want to build up front, and you need the describe it unambiguously to the agent. Also, even with a perfect request, agents often go down wrong paths and waste a lot of time and token costs doing the wrong thing.

That's not how I code personally. My process is more iterative, where I explore the problem and solution spaces as I build.

The other difference between aider and Workspaces is that currently aider is a terminal CLI tool. Although I just released a basic browser UI [1] the other day, making it more approachable for folks who are not fully comfortable on the command line.

[0] https://github.com/paul-gauthier/aider

[1] https://aider.chat/2024/05/02/browser.html

Aider was developed by Paul Gaither and focuses on giving developers a pair programming experience directly from developers' terminals. This command-line tool edits code in real-time based on a user prompt in the command terminal. As of writing, it only supports OpenAI’s API but can write, edit, and refine code across multiple languages including Python, JavaScript, and HTML. Developers can use Aider for code generation, debugging, and understanding complex projects.

I built a similar thing in python using Playwright and Pandoc [0]. It's used by aider's `/web ` command that lets you paste a markdown version of any webpage into your AI coding chat. This helps if you want to include docs for an obscure or non-public package/api/etc with the LLM while coding.

I really value dependencies which are easy for all users to install, cross-platform. Playwright is nice because it has a simple way to install its dependencies on most platforms. And the `pypandoc` module provides a seamless install of pandoc across platforms.

The result turns most web pages into nice markdown without requiring users to solve some painful platform specific chromium dependency nightmare.

[0] https://github.com/paul-gauthier/aider/blob/main/aider/scrap...

Thanks for trying aider, and sorry to hear you had trouble getting the hang of it. It might be worth looking through some of the tips on the aider GitHub page [0].

In particular, this is one of the most important tips: Large changes are best performed as a sequence of thoughtful bite sized steps, where you plan out the approach and overall design. Walk GPT through changes like you might with a junior dev. Ask for a refactor to prepare, then ask for the actual change. Spend the time to ask for code quality/structure improvements.

Not sure if this was a factor in your attempts? I'd be happy to help you if you'd like to open an GitHub issue [1] our jump into our discord [2].

[0] https://github.com/paul-gauthier/aider#tips

[1] https://github.com/paul-gauthier/aider/issues/new/choose

[2] https://discord.gg/Tv2uQnR88V

Have you tried something like Agentic’s Glide? (They announced it this week here on HN)

They use gpt, but they might be able to configure it so it uses Claude

Another tool to check out could be aider https://github.com/paul-gauthier/aider

Are you aware of the work on https://github.com/paul-gauthier/aider? What's your take on generating code diffs directly instead of code editing instructions?

He should add AI to his site!

Not really - the site is great as-is and there's nothing wrong with this approach. It looks like it works really well for Mr. 61.

But I'd imagine it'd be pretty helpful to write tools to help with maintaining the site which do leverage LLM models. Do a combination of search + AI to rewrite + reviewing the individual edits (e.g. through selective git adds).

I'm imagining a tool like https://github.com/paul-gauthier/aider (which I haven't tried yet, but it looks useful for this kind of effort).

I recently used [0] Playwright for Python and [1] pypandoc to build a scraper that fetches a webpage and turns the content into sane markdown so that it can be passed into an AI coding chat [2].

They are both very gentle dependencies to add to a project. Both packages contain built in or scriptable methods to install their underlying platform-specific binary dependencies. This means you don't need to ask end users to use some complex, platform-specific package manager to install playwright and pandoc.

Playwright let's you scrape pages that rely on js. Pandoc is great at turning HTML into sensible markdown. Below is an excerpt of the openai pricing docs [3] that have been scraped to markdown [4] in this manner.

[0] https://playwright.dev/python/docs/intro

[1] https://github.com/JessicaTegner/pypandoc

[2] https://github.com/paul-gauthier/aider

[3] https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turb...

[4] https://gist.githubusercontent.com/paul-gauthier/95a1434a28d...

  ## GPT-4 and GPT-4 Turbo

Thanks for trying aider, and sorry to hear you had trouble getting the hang of it. It might be worth looking through some of the tips on the aider github page:

https://github.com/paul-gauthier/aider#tips

In particular, this is one of the most important tips: Large changes are best performed as a sequence of thoughtful bite sized steps, where you plan out the approach and overall design. Walk GPT through changes like you might with a junior dev. Ask for a refactor to prepare, then ask for the actual change. Spend the time to ask for code quality/structure improvements.

Not sure if this was a factor in your attempts? But it's best not to ask for a big sweeping change all at once. It's hard to unambiguously and completely specify what you want, and it's also harder for GPT to succeed at bigger changes in one bite.