I'm looking to create a list of projects that people have had success with, whether they are personal projects that have no financial incentive or projects that have made money.
I'm also looking for videos that document the project from start to finish. The youtube algorithm makes these videos quite difficult to find.
Site for a drum and bass community. Isn't quite there but nearly - test.dnbfamily.com - EDIT: This is best viewed on a mobile at the moment
Completely vibe coded local LLM note formatter (I broke the latest release, need to fix) - https://formait.app/
Two android apps:
When you can't decide what to watch (swipe left + right like tinder) - https://play.google.com/store/apps/details?id=com.blazingban...
Bluetooth mesh app - https://play.google.com/store/apps/details?id=com.blazingban...
C# app that monitors trading performance of CTrader, locks down the application if your PNL goes too high or low (configurable) so that you don't lose all your money when you're tilted. Built for a friend that does a fair amount of trading.
So many little scripts and stuff for personal or work projects.
----
What are you trying to learn from the videos?
I've had fun with building the data loaded, website and mobile app via Claude Code from VS Code. However, I didn't find building the project as enjoyable as actual coding myself. The code is a mess and is definitely overengineered and hard to read. I have had to consistently fix bugs and calibrate my prompts so the machine could produced the features that I was trying to create.
Another thing I learned is to commit early and often. Then create PRs to check what code was updated as things got away from me quickly without me knowing or asking the machine to do the thing it did. A few times entire sections of code were removed that had nothing to do with the feature I was working on. Being able to go back to the previous working commit probably saved me hours.
Vibe coding an entire project was a good experience. There's a lot to learn and focus on the next time I go this route.
Take a look! https://mplscoffee.com
One suggestion: your “open now” toggle is confusing. I can’t tell what state it’s in without relying on inspecting one of the aggregates decreasing from 7 to 6. Use a non-color visual indicator (icons or words).
Last week I spent two days with Claude Code and was able to clean it up substantially, add a bunch of features and make it really useful. It's nice to be able to encounter a problem, write up a clear description, and have a working feature in less than an hour!
(aside) It's super important for an artist to keep track of their works, prices and where they are and as they get into the hundreds, it's impossible to untangle if you lose track. Also not all galleries are totally upfront and you often need to detect yourself that a piece has been sold and request your money since most sell on consignment.
Initially I built only the most basic features: paintings list with filter/search plus detail/edit, and galleries list with associated paintings and sold/unsold. At that point the app was too complex for the tools of last year to effectively build further.
In the last couple of days I added multi-currency, standardized pricing, exhibit details. Also the most important one, quick selections which are important for proposals, etc, together with a tidy little excel export and web-optimized image export for the selection.
It's been a fun project! I haven't released it yet but am considering it as a side project since I don't think the artist community is likely to buy tools like this in substantial numbers, unfortunately.
I also used CC to put together a static website[1] for my wife which I'm quite happy with. It was decent in one shot and basically done in a few hours!
[1]: https://elizakozurno.com
A non-developer (but PM) friend of mine vibe-coded his own strength-training programming app that he uses daily. He pivoted from that to vibe-coding his own 2d game engine and 4x strategy game he's been working on.
He's effectively used vibe-coding to teach himself how to code and he brings me questions/problems as good as any working junior developer.
[1] https://ironicsans.ghost.io/doomscrolling-the-game/
I'm currently building my own coding agent, VT Code. VT Code is a Rust-based terminal coding agent with semantic code intelligence via Tree-sitter (parsers for Rust, Python, JavaScript/TypeScript, Go, Java) and ast-grep (structural pattern matching and refactoring).
It supports multiple LLM providers: OpenAI, Anthropic, xAI, DeepSeek, Gemini, OpenRouter, Z.AI, Moonshot AI, all with automatic failover, prompt caching, and token-efficient context management. Configuration occurs entirely through vtcode.toml, sourcing constants from vtcode-core/src/config/constants.rs and model IDs from docs/models.json to ensure reproducibility and avoid hardcoding. [0], [1], [2]
Recently I've added Agent Client Protocol (ACP) integration. VT Code is now a fully compatible ACP agent, works with any ACP-clients: Zed (first-class support), Neovim, marimo notebook. [3]
[0] https://github.com/vinhnx/vtcode
[1] https://crates.io/crates/vtcode
[2] https://docs.rs/vtcode
[3] https://agentclientprotocol.com/overview/agents
Thank you!
Runs on Vercel free tier, costs nothing beyond the domain: https://www.hyroxtrainingplans.com/
Not perfect, but it's live and people use it.
https://github.com/MARTYR-X-LTD/livi
Backend is Rust and Frontend is SwiftUI. At some point I'll make a Libadwaita frontend for a Linux release. Given my knowledge in Swift and Rust is pretty limited, it was an interesting project to learn the strenghts and limits of LLMs. I've learned quite a lot with it. Most useful lesson is that you might not necessarily need to know the specifics of a language, but you do have to have your common sense skills sound and clear, and how to code architecture a larger project, with refactors here and there, performance optimizations, multithreading, queue, cache and logs, and so on.
Maybe needless to say, but it wasn't easy. The produced code needed to be inspected constantly, and bugfixing, testing, handling edge cases required tons of prompting and guidance. The comparison features, such as pinch to zoom, keep the zoom and image positions while switching between the different generated images, handling exporting, all these features were loaded with intricacies. So far, glad that I was able to produce this.
As a fun fact, now that AVIFENC supports tune=iq, we don't have to mess with specific encoder settings and find the proper quality number anymore, but still, learned a lot from it