mrge is an AI-powered code review platform that automatically reviews PRs and gives human reviewers superpowers. It’s tool of choice for fast-moving teams like cal.com and n8n.
Hey Product Hunt, Paul and Allis here – founders of mrge! 👋
We’re building mrge – an AI code review platform to help teams ship code faster with fewer bugs. Our early users include Cal.com, n8n, and Better Auth—teams that handle a lot of PRs every day.
We’re engineers who faced this problem when we worked together at our last startup. Code review quickly became our biggest bottleneck and quality tanked — especially as we started using AI to code more.
We had more PRs to review, subtle AI-written bugs slipped, and we (humans) found ourselves rubber-stamping PRs without deeply understanding the changes.
👷 We’re building mrge to help solve that. Here’s how it works:
Connect your GitHub repo via our Github app in two clicks (and optionally download our desktop app).
AI review: When you open a PR, our AI reviews your changes directly in a secure container. It has context into not just that PR, but your whole codebase, so it can pick up patterns and leave comments directly on changed lines. Once the review is done, the sandbox is torn down and your code deleted.
Human-friendly review workflow: Jump into our web (or desktop) app (it’s like Linear but for PRs). Changes are grouped logically (not alphabetically), with important diffs highlighted, visualized, and ready for faster human review.
💻 The AI reviewer works a bit like Cursor in the sense that it navigates your codebase using the same tools a developer would—like jumping to definitions or grepping through code.
⚡️ The platform itself focuses entirely on making *human* code reviews easier. A big inspiration came from productivity-focused apps like Linear or Superhuman, products that show just how much thoughtful design can impact everyday workflows. We wanted to bring that same feeling into code review.
That’s one reason we built a desktop app. It allowed us to deliver a more polished experience, complete with keyboard shortcuts and a snappy interface.
We think the future of coding isn’t about AI replacing humans—it’s about giving us better tools to quickly understand high-level changes, abstracting more and more of the code itself. As code volume continues to increase, this shift is going to become increasingly important.
🚀 mrge is free for 2 weeks. You also get 50% off for 2 months with the code: PHUNT
@masump Great question – under the hood, the AI navigates the codebase just like a real human would (eg grepping files, going to function definitions...) – which is how it handles large PRs. We also run various sub-agents that each specialize in finding specific issues, which helps "break down" large PRs into more manageable checks.
Technically, the way it works is that whenever you open a PR, mrge clones your repository and checks out your branch in a secure and isolated temporary sandbox. We provision this sandbox with shell access and a Language Server Protocol (LSP) server. The AI reviewer then reviews your code, navigating the codebase exactly as a human reviewer would—using shell commands and common editor features like "go to definition" or "find references". When the review finishes, we immediately tear down the sandbox and delete the code—we don’t want to permanently store it for obvious reasons.
Yep, that’s exactly what our custom rules are for. When you set up your account, we suggest a bunch of rules you can use—either based on your existing Cursor/Trae rules or even your team’s past comments in the repo. You can tweak them to match your style, so you’re not stuck with only generic linting.
Thanks for the kind words, @xinding! And really good question.
First off, huge props to Coderabbit—they set the stage for AI code review and helped put this whole space on the map. We've actually a lot of teams come over after trying several other review bots, including Coderabbit.
What we consistently hear from them is that:
Our AI review catches more relevant issues
The end-to-end platform is what lets their teams move much faster after the bot has commented. Eg. one feature our users love is that we group and order of files within PRs in the most logical way for reviewers to read (e.g., Backend changes > API > UI). On large PRs, that alone cuts review time in half.
We're really re-thinking the code-review experience from end-to-end, and I think that's why teams like cal.com prefer it.
Ultimately, I tell everyone to just try it yourself – it takes 2 clicks to install and you'll feel the difference!
Congrats on launching mrge, Paul and Allis 🎉 This looks like a smart solution to a growing problem, esp with the rise of Cursor, Windsurf etc. The codebase-aware reviews and logical grouping of changes sound particularly useful. Looking forward to trying this out on our repos!
Awesome idea! Does it support human-in-the-loop to escalate up when the confidence score is low on certain inference (e.g. feature vs. bug)?
Does it support compliance suggestions such as accessibility, security, privacy, etc?
Re: human-in-the-loop—it can’t directly escalate to a person (yet), but you can tag certain PRs or set custom rules so it knows when to flag things for manual review. We're working on deeper integrations here, so any feedback on what you'd want that to look like would be super helpful!
For compliance, yes—it supports suggestions for accessibility, security, privacy, etc. You can actually add your own custom checks if there are specific standards your team follows.
Love the UI advancements you all are outlining here, we need a lot more of this type of thinking now that we are post-AI and there is more code being generated than ever.
Any thoughts on how you this compares to greptile?
Big props to greptile—they really helped kick off the AI code review space and got a lot of people thinking seriously about this problem. We’ve actually had quite a few teams join us after trying greptile (and other review bots), so I hear this comparison a lot.
The main things we keep hearing from users are:
Our AI catches more relevant, actionable review issues for their codebase.
The full end-to-end platform makes reviews way faster, especially after the AI comments. One thing folks seem to love: we automatically group and order PR files in the most logical way (eg. backend changes > API > UI), so on big reviews, you don’t waste any time jumping around.
We’re really trying to rethink the whole code review workflow from the ground up. I think that’s why teams like cal.com and others have switched over to mrge.
Our goal is to make reviewing and shipping code just as fast and smooth as writing it (kind of like how Cursor changed the writing workflow for devs).
Always amazed me how advanced code editors had become, but how medieval PRs still felt lol. Mrge saves us about 6 hours per week (2 dev team). Not taking into account the spotting of details that tend to create ugly bugs which cost a lot more time and energy to fix once deployed to production.
Absolutely love how mrge speeds up reviews without losing depth. Caught a few issues we might have missed otherwise. Feels like a real productivity unlock!
Few feedback if it helps ( or at least making it impossible to use for our team): - It is awfully slow to browse around - When PR are made, subsequent push to the branch should trigger the review again
Thanks so much for the feedback—this is really helpful, and I totally get where you’re coming from.
We’re actively working on improving speed across the app. Also, you can actually trigger a re-review manually right now, but automating that after each push is something we’re exploring.
Out of curiosity, did mrge catch anything interesting in your recent PRs? Would love to make sure it’s actually adding value.
Oh I tried to look how I can trigger the review again but couldn't find. I will take a look again.
Not yet - but I know some time I'll make some catastrophic changes. I will come back here, and will let you know.
One winner feature for me would be: - People write ( especially me) not so perfect git commit messages. When merging the PR allow advance users to rebase with new git commit messages based on each commit diff). This will make my life easier and for other team members/understand the changes.
Minor comments: - I like the summary and the block diagrams of the changes - Why all comments are not published to the github pr? I think it will help as any reviewer to go to the github pr and understand the changes. I understand the vision is to make the mrge as default review PR platform but I guess getting everyone familiar with the mrge comments should become like a necessity on the PR - Low hangings can be - integrate with some git hooks? ( Kind of forcing the team to use mrge ha ha) - Update the PR description based on new changes if needs be
Yes, mrge supports Rust! Under the hood, we spin up an LSP server for your repo, and Rust is one of the languages we support out of the box.
For CI/CD integration: mrge automatically runs reviews as part of your existing CI workflow. As soon as a PR is opened, we spin up a secure, temporary sandbox, clone your code, and the AI kicks off its review. The results show up as PR comments and can be surfaced alongside your normal CI/CD checks—so your team doesn’t have to change anything about how you work.
Let me know if you have any more questions, or want a walkthrough on how it plugs into your CI setup!
Thanks @francescu ! Really glad to hear you enjoyed the experience—we put a lot of thought into making sure the AI feels genuinely helpful without getting in your way. If you have any suggestions or ideas as you keep using it, let us know!
Replies
Hey Product Hunt, Paul and Allis here – founders of mrge! 👋
We’re building mrge – an AI code review platform to help teams ship code faster with fewer bugs. Our early users include Cal.com, n8n, and Better Auth—teams that handle a lot of PRs every day.
🚀 See it in action for cal.com here
We’re engineers who faced this problem when we worked together at our last startup. Code review quickly became our biggest bottleneck and quality tanked — especially as we started using AI to code more.
We had more PRs to review, subtle AI-written bugs slipped, and we (humans) found ourselves rubber-stamping PRs without deeply understanding the changes.
👷 We’re building mrge to help solve that. Here’s how it works:
Connect your GitHub repo via our Github app in two clicks (and optionally download our desktop app).
AI review: When you open a PR, our AI reviews your changes directly in a secure container. It has context into not just that PR, but your whole codebase, so it can pick up patterns and leave comments directly on changed lines. Once the review is done, the sandbox is torn down and your code deleted.
Human-friendly review workflow: Jump into our web (or desktop) app (it’s like Linear but for PRs). Changes are grouped logically (not alphabetically), with important diffs highlighted, visualized, and ready for faster human review.
💻 The AI reviewer works a bit like Cursor in the sense that it navigates your codebase using the same tools a developer would—like jumping to definitions or grepping through code.
⚡️ The platform itself focuses entirely on making *human* code reviews easier. A big inspiration came from productivity-focused apps like Linear or Superhuman, products that show just how much thoughtful design can impact everyday workflows. We wanted to bring that same feeling into code review.
That’s one reason we built a desktop app. It allowed us to deliver a more polished experience, complete with keyboard shortcuts and a snappy interface.
We think the future of coding isn’t about AI replacing humans—it’s about giving us better tools to quickly understand high-level changes, abstracting more and more of the code itself. As code volume continues to increase, this shift is going to become increasingly important.
🚀 mrge is free for 2 weeks. You also get 50% off for 2 months with the code: PHUNT
Just sign up with your Github account to get started!
Looking forward to your feedback—fire away!
@paul_sangle_ferriere1 Amazing work! How does mrge handle very large PRs with cross-file dependencies?
@masump Great question – under the hood, the AI navigates the codebase just like a real human would (eg grepping files, going to function definitions...) – which is how it handles large PRs. We also run various sub-agents that each specialize in finding specific issues, which helps "break down" large PRs into more manageable checks.
Technically, the way it works is that whenever you open a PR, mrge clones your repository and checks out your branch in a secure and isolated temporary sandbox. We provision this sandbox with shell access and a Language Server Protocol (LSP) server. The AI reviewer then reviews your code, navigating the codebase exactly as a human reviewer would—using shell commands and common editor features like "go to definition" or "find references". When the review finishes, we immediately tear down the sandbox and delete the code—we don’t want to permanently store it for obvious reasons.
@paul_sangle_ferriere1 Kudos! I was wondering if it can be used for reviewing opinionated code style? Maybe use existing cursor/trae rules?
@rahool_lol Hey Rahul, thanks for the kind words!
Yep, that’s exactly what our custom rules are for. When you set up your account, we suggest a bunch of rules you can use—either based on your existing Cursor/Trae rules or even your team’s past comments in the repo. You can tweak them to match your style, so you’re not stuck with only generic linting.
Congrats on the launch! How does it compare to https://www.coderabbit.ai/?
Thanks for the kind words, @xinding! And really good question.
First off, huge props to Coderabbit—they set the stage for AI code review and helped put this whole space on the map. We've actually a lot of teams come over after trying several other review bots, including Coderabbit.
What we consistently hear from them is that:
Our AI review catches more relevant issues
The end-to-end platform is what lets their teams move much faster after the bot has commented. Eg. one feature our users love is that we group and order of files within PRs in the most logical way for reviewers to read (e.g., Backend changes > API > UI). On large PRs, that alone cuts review time in half.
We're really re-thinking the code-review experience from end-to-end, and I think that's why teams like cal.com prefer it.
Ultimately, I tell everyone to just try it yourself – it takes 2 clicks to install and you'll feel the difference!
Congrats on launching mrge, Paul and Allis 🎉 This looks like a smart solution to a growing problem, esp with the rise of Cursor, Windsurf etc. The codebase-aware reviews and logical grouping of changes sound particularly useful. Looking forward to trying this out on our repos!
Thanks @merlin_k , great to hear that.
Feel free to email / DM if you have any feedback!
SyncSignature
This can be a huge time saver!
Thanks Neel, great to hear it's resonating!
Brev
Hey Vic, thanks for the questions! 🙌
Re: human-in-the-loop—it can’t directly escalate to a person (yet), but you can tag certain PRs or set custom rules so it knows when to flag things for manual review. We're working on deeper integrations here, so any feedback on what you'd want that to look like would be super helpful!
For compliance, yes—it supports suggestions for accessibility, security, privacy, etc. You can actually add your own custom checks if there are specific standards your team follows.
Love the UI advancements you all are outlining here, we need a lot more of this type of thinking now that we are post-AI and there is more code being generated than ever.
Any thoughts on how you this compares to greptile?
@snowandcaffeine Great question!
Big props to greptile—they really helped kick off the AI code review space and got a lot of people thinking seriously about this problem. We’ve actually had quite a few teams join us after trying greptile (and other review bots), so I hear this comparison a lot.
The main things we keep hearing from users are:
Our AI catches more relevant, actionable review issues for their codebase.
The full end-to-end platform makes reviews way faster, especially after the AI comments. One thing folks seem to love: we automatically group and order PR files in the most logical way (eg. backend changes > API > UI), so on big reviews, you don’t waste any time jumping around.
We’re really trying to rethink the whole code review workflow from the ground up. I think that’s why teams like cal.com and others have switched over to mrge.
Our goal is to make reviewing and shipping code just as fast and smooth as writing it (kind of like how Cursor changed the writing workflow for devs).
Hey! Congrats on the product launch — I really love what you’ve built.
I put together a quick redesign of your website to better showcase mrge's value. Thought you might like to check it out: https://www.figma.com/community/file/1499461191851219376/banker-portfolio
Always amazed me how advanced code editors had become, but how medieval PRs still felt lol. Mrge saves us about 6 hours per week (2 dev team). Not taking into account the spotting of details that tend to create ugly bugs which cost a lot more time and energy to fix once deployed to production.
Thanks @rauf_akdemir , that's great to hear!
Absolutely love how mrge speeds up reviews without losing depth. Caught a few issues we might have missed otherwise. Feels like a real productivity unlock!
DataSci.Pro
Congrats!
Awesome work guys! Absolutely love the product.
Awesome product - we love using mrge.
Congrats on the launch!!
Few feedback if it helps ( or at least making it impossible to use for our team):
- It is awfully slow to browse around
- When PR are made, subsequent push to the branch should trigger the review again
@yardstick17 Hey Amit,
Thanks so much for the feedback—this is really helpful, and I totally get where you’re coming from.
We’re actively working on improving speed across the app. Also, you can actually trigger a re-review manually right now, but automating that after each push is something we’re exploring.
Out of curiosity, did mrge catch anything interesting in your recent PRs? Would love to make sure it’s actually adding value.
@paul_sangle_ferriere1
Oh I tried to look how I can trigger the review again but couldn't find. I will take a look again.
Not yet - but I know some time I'll make some catastrophic changes. I will come back here, and will let you know.
One winner feature for me would be:
- People write ( especially me) not so perfect git commit messages. When merging the PR allow advance users to rebase with new git commit messages based on each commit diff). This will make my life easier and for other team members/understand the changes.
Minor comments:
- I like the summary and the block diagrams of the changes
- Why all comments are not published to the github pr? I think it will help as any reviewer to go to the github pr and understand the changes. I understand the vision is to make the mrge as default review PR platform but I guess getting everyone familiar with the mrge comments should become like a necessity on the PR
- Low hangings can be - integrate with some git hooks? ( Kind of forcing the team to use mrge ha ha)
- Update the PR description based on new changes if needs be
Does this support Rust? Also, does it integrate/understand regular CI/CD results?
Hey @shreyash_nigam , great questions!
Yes, mrge supports Rust! Under the hood, we spin up an LSP server for your repo, and Rust is one of the languages we support out of the box.
For CI/CD integration: mrge automatically runs reviews as part of your existing CI workflow. As soon as a PR is opened, we spin up a secure, temporary sandbox, clone your code, and the AI kicks off its review. The results show up as PR comments and can be surfaced alongside your normal CI/CD checks—so your team doesn’t have to change anything about how you work.
Let me know if you have any more questions, or want a walkthrough on how it plugs into your CI setup!
Rebank
Congrats on the launch, team!
@simonwhite87 Thank you! Looking forward to hearing what you and your team think 🙂
Mojo
I played with it and I love how AI is used in a smart, discreet, way. Good job!
Thanks @francescu ! Really glad to hear you enjoyed the experience—we put a lot of thought into making sure the AI feels genuinely helpful without getting in your way. If you have any suggestions or ideas as you keep using it, let us know!
not a developer myself, but shared this with dozens of freelancers and agencies who instantly loved it
Thanks @jason_chernofsky , that means a lot!
ClipDrop
Very cool. Congrats!
Thanks Damien!
Thanks German!