Codeball finds bugs in your Pull Requests, lets you ship faster and with higher confidence. The Codeball AI is trained on millions of code contributions to recognise risky code changes.
Hey fellow builders!
I'd like to show you something we recently built at Sturdy (W21).
Codeball is a code review AI which approves safe Pull Requests that a human would have approved. We hate waiting for reviews.
This started off as scratching our own itch in answering "How predictable are programmers?" Very predictable, turned out to be the answer.
Codeball is trained on over 1M Pull Requests, so it has seen tons of failure (shitty code) and success (decent code) patterns, making it really good at telling the difference.
You can play with it at codeball.ai where you can do "historical" tests on GitHub repos to see what Codeball would have done.
Using AI for mundane reviews saves a bunch of time, but the part that's really cool is that once you stop rubber stamping every single PR, you pay more attention to the tricky ones.
You can add Codeball to your repository as a GitHub Action (takes like 2 minutes).
Try for free!
Codeball is currently used by over 100 open-source repositories, including HUGE communities like gogs, kratos, and emqx!
“This is incredible, don’t forget to charge us!” – CEO
“I love it, developers are now trying to ‘cheat’ the system by creating smaller PRs, just like I’ve been telling them to!” – Senior Software Engineer
Also a bunch more in the Hacker News thread that made front page recently.