Launch HN: mrge.io (YC X25) – Cursor for code review

221 points by pomarie ↗ HN
Hey HN, we’re building mrge (https://www.mrge.io/home), an AI code review platform to help teams merge code faster with fewer bugs. Our early users include Better Auth, Cal.com, and n8n—teams that handle a lot of PRs every day.

Here’s a demo video: https://www.youtube.com/watch?v=pglEoiv0BgY

We (Allis and Paul) are engineers who faced this problem when we worked together at our last startup. Code review quickly became our biggest bottleneck—especially as we started using AI to code more. We had more PRs to review, subtle AI-written bugs slipped through unnoticed, and we (humans) increasingly found ourselves rubber-stamping PRs without deeply understanding the changes.

We’re building mrge to help solve that. Here’s how it works:

1. Connect your GitHub repo via our Github app in two clicks (and optionally download our desktop app). Gitlab support is on the roadmap!

2. AI Review: When you open a PR, our AI reviews your changes directly in an ephemeral and 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 – we don’t store it for obvious reasons.

3. Human-friendly review workflow: Jump into our web 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.

But a big challenge was that, unlike Cursor, mrge doesn’t run in your local IDE or editor. We had to recreate something similar entirely in the cloud.

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.

We know cloud-based review isn't for everyone, especially if security or compliance requires local deployments. But a cloud approach lets us run SOTA AI models without local GPU setups, and provide a consistent, single AI review per PR for an entire team.

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.

Beyond performance, the main thing we care about is making it easier for humans to read and understand code. For example, traditional review tools sort changed files alphabetically—which forces reviewers to figure out the order in which they should review changes. In mrge, files are automatically grouped and ordered based on logical connections, letting reviewers immediately jump in.

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.

You can sign up now (https://www.mrge.io/home). mrge is c...

109 comments

[ 5.0 ms ] story [ 185 ms ] thread
This looks like a cool solve for this problem. Some of the other tools I tried didn't seem to contextualize the app, so the comments were surface level and trite.

I'm on Bitbucket so will have to wait :)

Thanks, really appreciate that! Yeah, giving the AI the ability to fetch the context it needs was a big challenge (since larger codebases can't all fit in an LLM's context window)

And totally hear you on Bitbucket—it's definitely on our roadmap. Would love to loop back with you once we get closer on that front!

It looks like graphite.dev has pivoted into this space too. Which is annoying, because I'm interested in graphite.dev's core non-AI product. Which appears to be stagnating from my perspective -- they still don't have gitlab support after several years.
Yeah, noticed that too—what's the core graphite.dev feature you're interested in? PR stacking, by chance?

If that's it, we actually support stacked PRs (currently in beta, via CLI and native integrations). My co-founder, Allis, used stacked PRs extensively at her previous company and loved it, so we've built it into our workflow too. It's definitely early-stage, but already quite useful.

Docs if you're curious: https://docs.mrge.io/overview

Yes, stacked PR's and a rebase-only flow. Unfortunately we're a GitLab shop. Today's task is a particularly hairy review; it's too bad I can't try you out.
Ah, totally get it—that’s frustrating. GitLab support is on our roadmap, so hopefully we can help you out soon.

In the meantime, good luck with that hairy review—hope it goes smoothly! If you're open to it, I'd love to reach out directly once GitLab support is ready.

Email is in profile. You're welcome to add me to your list.
Same. I'm not at all impressed with Graphite as a code stacking tool; Aviator looks much nicer. But I recently started using Graphite's AI review tool, and it's also really poor. Out of all the suggested corrections so far, all were wrong except one that fixed an obvious typo in a comment.
This is an awesome direction. Few thoughts:

It would be awesome if the custom rules were generalized on the fly from ongoing reviewer conversations. Imaging two devs quibble about line length in a PR, and in a future PR, the AI reminds about this convention.

Would this work seamlessly with AI Engineers like Devin? I imagine so.

This will be very handy for solo devs as well, even those who don't use Coding CoPilots could benefit from an AI reviewer, if it does not waste their time.

Maybe there can be multiple AI models review the PR at the same time, and over time, we promote the ones whose feedback is accepted more.

These are all amazing ideas. We actually already see a lot of solo devs using mrge precisely because they want something to catch bugs before code goes live—they simply don't have another pair of eyes.

And I absolutely love your idea of having multiple AI models review PRs simultaneously. Benchmarking LLMs can be notoriously tricky, so a "wisdom of the crowds" approach across a large user base could genuinely help identify which models perform best for specific codebases or even languages. We could even imagine certain models emerging as specialists for particular types of issues.

Really appreciate these suggestions!

Appreciate the feedback! We currently auto-suggest custom rules based on your comment history (and .cursorrules), however continuing to suggest from history is now on the roadmap thanks to your suggestion!

On working with Devin: Yes, right now we're focused on code review, so whatever AI IDE you use would work. In fact, it might even be better with autonomous tools like Devin since we focus on helping you (as a human) understand the code they've written faster.

Interesting idea on multiple AI models --we were also separately toying with the idea of having different personas (security, code architecture), will keep this one in mind!

Line length isn't something I'd want reviewed in a PR. Typically I'd set up a linter with relevant limits and defer to that, ideally using pre-commit testing or directly in my IDE. Line length isn't an AI feature, it's largely a solved problem.
I see on your website that you claim the subprocessors are SOC2 type 2 certified, but it doesn't appear that you claim anything about your SOC2 status (in progress, certified, not interested). I mention this because I would suspect the breach risk is not that OpenAI gets popped but rather that a place which gathers continuously updated mirrors of source code does. The sandbox idea only protects the projects from one another, not from a malicious actor injecting some bad dep into your supply chain
That's a very good point. We actually just kicked off our own SOC 2 certification process last week—I hadn't updated the website yet, but I'll go ahead and do that now. Thanks for raising this!

Appreciate the feedback around security as well; protecting against supply-chain attacks is definitely top of mind for us as we build this out.

I know I'm not supposed to mention website issues here, but since you brought it up I wanted to bring to your attention that the "fade in on scroll" isn't doing you any favors for getting the information out of your head and into the heads of your audience. That observation then went to 11 when I scrolled back up and the entire page was solid black, not even showing me the things it had previously swooshed into visibility. It's your site, do what makes you happy, but I just wanted to ensure you were aware of the tradeoff you were making
Hey, thanks again—really appreciate the heads-up! Could you point me to the specific section where you're seeing the fade in on scroll? Also, what browser are you using?

I don't remember adding that feature so it might be a bug

All of them? Firefox 137 on macOS Intel

After watching it sit there for 5-10 seconds before loading the section 'data-framer-name="Join"' I decided to inspect the element after it did load to see what it was doing. That's when I spotted all the JS and data attributes implying it was likely built with one of those drag-and-drop site builders, which explains why it may be behaving in an unexpected way for you. It also explains why it may default to "fade in on scroll" behavior, if my experience is any indication, because marketing folks _love_ that shit

That's so weird – I can't repro at all! I'll keep digging.. If anyone else reading this is also experiencing this, please shout!
As far as I can see, this doesn't directly integrate with github (we currently use coderabbit on github)? Is it on your timeline?
good question! we currently support a direct integration with github via a github app. we'll make that clearer in the post.
One personal niggle: "Code Review For The AI Era". I hate when people say era in relation to AI because it reminds me of Google's tasteless Gemini era thing.
that makes total sense, thanks for the feedback! we debated this for a bit--will keep in mind for the next design pass on the site :)
I've tried something similar in the past. The concept is cool, but so far the solutions I've seen are not so useful in terms of comments quality and ability to catch bugs.

Hope this is the right time, as this would be a huge time-saver for me

We had heard the same from a few early users, but they've commented that our AI is a more context aware/useful. Of course, that's just anecdotal. We'd love to give you a free trial (https://mrge.io/invite?=hn) and get your feedback on quality/bug catching. Feel free to reach out at contact@mrge.io if you have any questions too!
I was wondering if it has information about previous commits with deleted code? Sometimes we make a change and later realize that the previous code worked better, would mrge be able to understand that?
that's a good question! today, we don't look at previous commits--but thats something that we'll consider for future roadmap. curious if this happens often to your team? and if so, how you general gauge "better" (on the prev commits)
How does this work for large monorepos?

If the repo is several GB, will you clone the whole thing for every review?

good q! today, we'd clone the whole thing, but we're actively looking into solutions about that atm (ie: only cloning the relevant subdirs)

for custom rules, we do handle large monorepos by allowing you to add an allowlist (or exclude list) via glob patterns.

Happy mrge user here - congrats on the launch! It’s encouraged our team to do more stacked PRs and made every review a bit nicer
Really appreciate the feedback, really happy it's helping you :)
thanks Tim! So glad it's been helping your team move faster
If you are looking for an alternative that can also chat with you in Slack, create PRs, edit/create/search tickets and Linear, search the web and more, check out codegen.com
Excellent product, congrats on the launch guys!
Would be great to have support for GitLab also (have a project there that I would love to try this on and I can't switch it to GitHub)
On the roadmap! If you're happy to share your email for an early link when we do support it, send to contact@mrge.io
Honest initial reaction to your pitch: > Cursor for code review

Isn't cursor already the "cursor for code review?"

appreciate the honest reaction! We'll think about this more, what we were trying to get at is that cursor is more about code writing, and we're tackling the review/collaboration side :) curious if anything else would have immediately stuck out to you more?
I think I got the pitch meaning immediately: this is a specialized ai tool for code review.

That said, that doesn't sound like something very useful when I already use an ai code editor for code review. And github already supports automations for ci/ci for ai tools for code review. Maybe I just don't see value in an extra tool for this.

Congrats on the launch. Another happy user here. (Caught a really sneaky issue too!)
Thanks for sharing that Jof! Glad it's helpful :)
I wanted to check this out, so I installed the GitHub app on my account, with access to all my personal repos. However when I went looking for one of my repos (auscompgeek/sphinxify) I couldn't find it. It looks like I can only see the first 100 repos in the dashboard? I have a lot of forks under my account…
Quick update – we've merged a fix which should be live in ~15 mins! Thanks for reporting this :)
I've used CodeRabbit for Code Review. It does pretty cool work.

How different it is from that?

Great question!

We've heard from users who've tried both that our AI reviewer tends to catch more meaningful issues with less noise, that's really something you should try for yourself and find out! (The great thing is that it's really easy to start using)

Beyond the AI agent itself (which is somewhat similar to CodeRabbit), our biggest differentiation comes from the human review experience we've built. Our goal was to create a Linear-like review workflow designed to help human reviewers understand and merge code faster.

in the demo video i see that you can apply a recommended code change with one click. how do you make sure that the code still works after the AI changes?

also, i tried some other ai review tools before. one big issue was always that they are too nice and even miss obvious bad changes. did you encounter these problems? did you mitigate this via prompting techniques or finetuning?

Great questions!

For applying code changes with one-click: we keep suggestions deliberately conservative (usually obvious one-line fixes like typos) precisely to minimize risks of breaking things. Of course, you should confirm suggestions first.

Regarding AI reviewers being "too nice" and missing obvious mistakes—yes, that's a common issue and not easy to solve! We've approached it partly via prompt-tuning, and partly by equipping the AI with additional tools to better spot genuine mistakes without nitpicking unnecessarily. Lastly, we've added functionality allowing human reviewers to give immediate feedback directly to the AI—so it can continuously learn to pay attention to what's important to your team.

thanks for answering! will definitly check out the tool when i have the chance. best of luck building this!
> We know cloud-based review isn't for everyone, especially if security or compliance requires local deployments. But a cloud approach lets us run SOTA AI models without local GPU setups, and provide a consistent, single AI review per PR for an entire team.

I feel like that’s being overlooked here a bit too briefly. Is your target market not primarily larger teams who are most likely to have some security and privacy concerns?

I guess is there something on the roadmap to maybe offer something later ?

Definitely—larger teams do typically have more stringent security and privacy requirements, especially if they're already using self-hosted GitHub. Self-hosted or hybrid deployment is definitely on our radar, and as we grow, it's likely we'll offer a self-hosted version specifically to support those larger teams.

If that's something your team might need, I'd love to chat more and keep you posted as we explore this!

happy user here—our team moved from coderabbit to mrge, and everyone seems to love how much more useful the AI comments are
Really happy to hear mrge is useful! :) Thanks for sharing
thanks for the feedback! Glad that our ai reviewer has been useful to your team!
why not GitHub Copilot?
Great question!

We've heard from users who've tried both that our AI reviewer tends to catch more meaningful issues with less noise, that's really something you should try for yourself and find out! (The great thing is that it's really easy to start using)

Beyond the AI agent itself (which is somewhat similar to Copilot), our biggest differentiation comes from the human review experience we've built. Our goal was to create a Linear-like review workflow designed to help human reviewers understand and merge code faster.

you are in rough competition. competing with GitHub (Microsoft) for model quality, inference cost, and GitHub UI integration (one button click, comment replies, code diff, reset of GitHub UI ecosystem), don't start me about training of LLMs... and likely they will not break down Microsoft anytime soon. it is going to be tough!
Great that AI seemingly revives the stalled PR / review space. I just hope that human and local workflows will not be an afterthought or even made harder by these tools. Its also a great chance for stacked PRs and jujutsu to shake up the market.
Definitely! As AIs write a lot more code, I think that the PR/review space is going to become way more important.

If you're interested in Stack PRs, you should definitely check them out on Mrge. By the way, we natively support them (in beta atm): https://docs.mrge.io/ai-review/overview

The beta setting of stacked PRs seems to have no effect for me. Reading the mention of a cli in the docs for PR stacks gives me shivers. Please don't say you are implement it like graphite, which is the absolute worst way to do it and makes graphite useless for every sapling and jujutsu user that would need it most. You can also reach me at mrge@ntr.io would be happy to chat!
I've been evaluating AI code review vendors for my org. We've trialed a couple so far. For me, taking the workflow out of GitHub is a deal breaker. I'm trying to speed things along, not upend my whole team's workflow. What's your take on that?
Yeah, that's a totally legit point!

The good news with mrge is that it works just like any other AI code reviewer out there (CodeRabbit, Copilot for PRs, etc.). All AI-generated review comments sync directly back to GitHub, and interacting with the platform itself is entirely optional. In fact, several people in this thread mentioned they switched from Copilot or CodeRabbit because they found mrge's reviews more accurate.

If you prefer, you never need to leave GitHub at all.