fmerian

Watermelon - Open source copilot for code review

by
For software engineering teams that spend a lot of time reviewing pull requests, we provide an open-source copilot for code review.

Add a comment

Replies

Best
Naveed Rehman
first, logo is so cool! second, aren't there a few ai tools already available? whats your unique value? congratz
Esteban Vargas
@naveed_rehman there's a new breed of innovative tools adding AI to their products to expedite code review. That's correct. Being open-source is key to differentiation. As developers, we prefer to install open stuff. We trust those products more. In addition to that, I want to give you a glimpse of something that's already having a test PR: We'll give you the ability to choose your model of preference if you're more inclined towards an OSS alternative to Open AI such as Mistral. Beyond that and what's most important is that contrary to all these other products, we understand that we need to trace code context for LLMs to produce the best results.
Daxeel Soni
Congrats on the Watermelon launch! It's fantastic to see tools that streamline the code review process. I'm excited about the potential time-saving benefits for engineering teams. Keep up the great work!
Esteban Vargas
@daxeelsoni thanks for your support! We’ve identified code review is a very common bottleneck for engineering teams, therefore we’re laser-focused on solving this. May I ask, is your team’s bottleneck more around velocity or stability?
Hossein Yazdi
This is so time-saving. Especially for those repositories who get tons of pull requests in a short amount of time. Great product guys and congrats on your launch.
Esteban Vargas
@hosseinyazdi 100%. Repos with a lot of PRs are the ones that get the best use case. Very curious to learn: What is it exactly about the product that catches your attention the most?
Esteban Dalel Rueda
@hosseinyazdi Messy repos are the ones that get the most out of us, do you have any examples we can look at?
George Livingston
Looks cool..
Esteban Vargas
@george_livingston Thanks! Is there anything in particular that you really like?
Luca Repetto
Hey @helloteban, what an incredible feat you've achieved! It's inspiring to see a product that focuses on helping code reviewers. We're really excited to see the impact that this watermelon can have on the programming community. All the best!
Esteban Vargas
@rep_eat Thanks, and more than happy to guide you through the process of using our product! Anything that you particularly like that we should double down on?
Fabio Espinosa
Uhh I spend hours on code reviews daily, can totally see how this can help. Gonna give it a try!
Esteban Vargas
@fabioespinosa Thanks! Would love to pick your brain on this. What efforts is your team currently making to reduce this amount of time?
Rook Fallon
Awesome product!
Esteban Vargas
@rook_fallon Thanks! Is there anything in particular that you really like?
Rohan Singhvi
💎 Pixel perfection
Congrats on the launch @helloteban ! Will get our team to surely try this out. Small feedback on your website, the initial scrolling laptop animation has a bit of an issue! Do check that out... Anyways really rooting for the product!
Esteban Vargas
@rohan_singhvi1 Thanks! Yeah the website does need some work. Are you on mobile or desktop?
Saroj
@helloteban : Congrats on the launch team, the product looks amazing.
Hiro - Atsuhiro Teshima
Hey Esteban, I remember seeing watermelon long ago at the Pioneer tournament! It is great to see the project made a lot of progress and launched on ProductHunt. Congrats on the launch! I think it would be great if teams could add some rules for the PR. For example, if the PR size is too large, advise the developer to split the PR into multiple small PRs.
Esteban Vargas
@atsuhiro_teshima Woah that was very long ago! We were not even building a dev tool back then. It's been so long in retrospect. Thanks for your support! We've been thinking about adding something like this to our rules engine. For instance, we know that certain companies have a rule that says "a PR shouldn't exceed 200 LOC". What's going on around our heads is "how do we make this not so opinionated, but at the same time not so unopinionated as including the X number of LOC as a settings parameter?" "Is number of LOC the best proxy for everyone in the first place?" Would you please give us some advice on this? How do you recommend we think about it?