Launch HN: mrge.io (YC X25) – Cursor for code review
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 ] threadI'm on Bitbucket so will have to wait :)
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!
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
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.
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.
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!
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!
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 don't remember adding that feature so it might be a bug
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
Hope this is the right time, as this would be a huge time-saver for me
If the repo is several GB, will you clone the whole thing for every review?
for custom rules, we do handle large monorepos by allowing you to add an allowlist (or exclude list) via glob patterns.
Isn't cursor already the "cursor 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.
How different it is from that?
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.
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?
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.
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 ?
If that's something your team might need, I'd love to chat more and keep you posted as we explore this!
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.
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 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.