AI Code Reviews that automatically catch logical bugs, anti-patterns, documentation drift, and can even enforce your team style guide. Simply open a PR to get a code review. Then, if any bugs are found, squash them with 1-click Bug Fixes. Free trial available.
Hi ProductHunt, Hunter and Nick here!
Allow me to introduce Ellipsis, a GitHub bot that automatically performs deep, LLM-powered code reviews, fills in PR descriptions, and can even write working, tested code to fix bugs.
Simply open a pull request to get an AI Code Review and summary. As you keep pushing code, Ellipsis will update the summary and review the new changes. If a bug pops up, you can squash it with 1-click fixes.
🚀 Here's an example from jxnl/instructor (10K stars) 🚀
👨💻 What does it catch?
Ellipsis will catch logical errors, anti-patterns, security issues, spelling & grammar mistakes, documentation drift, and more. Reviews take less than 3 minutes. You can even have Ellipsis enforce your team style guide rules, like this project. For example, you might add a rule like "Make sure new code has corresponding unit tests." Ellipsis will subsequently leave reminders on any pull requests that try to submit untested code.
🐛 How does it fix bugs?
When Ellipsis finds a problem, it'll leave a comment on the offending line, just like a human would. Then, you can tag Ellipsis to have it implement the fix. This allows you to write working, tested code right from the GitHub UI! Internally, Ellipsis actually tests the code it writes by building your project, running the unit tests, linter, etc. 🆒
🚀 Why did we build this?
We built Ellipsis because we are TIRED of the status quo code review process: create a PR, ask for review, move on to new task, receive feedback, reacquaint with old code, fix bug, go back to new task... there's too much context switching. With Ellipsis, the reviews are nearly instant and addressing feedback doesn't require checking out an old branch.
❓ Does it work?
Yes. State-of-the-art LLM's aren't good enough (yet) to implement entire features, but they are good enough to catch and fix small mistakes in code. Our data shows that teams that use Ellipsis merge pull requests 13% faster than those that don't. Typically, a developer will get a "Looks good to me!" from Ellipsis before asking for a peer review, resulting in a higher quality discussions with fewer [nit] comments.
Start a free trial to get 7 days of AI Code Reviews at ellipsis.dev 🤖
I love the idea of having an AI assistant to help keep my code clean and efficient.
What differentiates Ellipsis from other solutions in this space, and how do you envision its long-term impact on the market?
That's fantastic. Happy to see a tool that tackles the common pain points in the code review process. It effectively enhances development workflows and boosts productivity across teams. All the best for the launch!
This is a great idea - looking forward to trying this out. Have been a bit disappointed with other tools that offer to write tests for me. The pricing seems pretty fair as well!
Ha LGTM-as-a-service! Love the little humor there. This honestly is a great addition especially if the team is stretched super thin and tech leads don't have time to do good code reviews. I've seen junior engineers suffer because tech leads don't give good reviews and they leave as a result.
I assume the AI can leverage style guide you created so it will stay consistent and personalize the reviews?
Congrats on the launch @hunter_brooks and team!
Super exciting stuff! Definitely going to try this out to save precious dev time on our small team. Curious if you have any plans to expand the integrations available for the standup reports feature to other platforms (e.g. Teams, Discord, etc.)
Saw this on ProductHunt, kind of skeptical about using an AI for code reviews, can it really catch bugs as well as a human? definitely worth a try though
Congrats on the launch! Ellipsis looks like a powerful tool for speeding up code reviews and catching bugs early. Excited to see how it helps teams be more efficient!
Wow, Ellipsis looks really impressive! I love the idea of automated, AI-powered code reviews that can catch a wide range of issues and even implement fixes. The instant feedback and reduced context switching could be a game-changer for dev teams.
Some thoughts on potential improvements:
1) It would be great to see how Ellipsis compares to other code review tools like DeepCode or Amazon CodeGuru in terms of accuracy and coverage. Maybe you could share some benchmarks?
2) Have you considered adding support for more languages beyond what GitHub natively supports? Tools like SonarQube offer analysis for 27+ languages.
3) It might be helpful to allow customizable sensitivity levels for different types of issues, similar to how ESLint has configurable rule severities.
4) Integration with CI/CD pipelines could be a nice addition, automatically blocking merges if Ellipsis finds critical issues.
Overall, Ellipsis seems like a valuable tool that could significantly streamline the code review process. Looking forward to seeing how it evolves!
I think this tool will make code maintenance a lot easier. The integration of bug detection and style enforcement is pretty innovative!
I’m excited about this tool! The automatic bug detection and style guide enforcement sound like they’ll make code reviews much smoother.
