Why does it require signing and granting you full access to act as me on Github to use?
cmux-agent requires access to your Github account:
Verify your GitHub identity
Know what resources you can access
Act on your behalf
View your email addresses
Public repos shouldn't require being signed in.
Just tested these example links in incognito and seemed to work?
https://0github.com/manaflow-ai/cmux/pull/666
https://0github.com/stack-auth/stack-auth/pull/988
https://0github.com/tinygrad/tinygrad/pull/12995
https://0github.com/simonw/datasette/pull/2548
> you've disabled logging issues on the repo
Sorry, wasn't aware. Turning it on right now. EDIT: https://github.com/manaflow-ai/cmux/issues seems to be fine?
It is GitHub mess. See the discussion: https://github.com/orgs/community/discussions/37117
To keep it short, GitHub has oauth App and "GitHub Apps". GitHub Apps are the new model and they can be installed to particular repos instead of having wide access to your account. GitHub recommends you use them. There is one catch however: GitHub did architecture these apps so that they can "act on the user behalf". Even if your app only asks for "an email address", they will still have that "permission" even though it is against nothing.
Thus, the scary popup. I've found the only solution to this is to "complicate" your flow. If you go to https://codeinput.com (my app), and click login with GitHub, you'll be taken to a less scarier popup that only asks for your email (it's an oauth app!). This, however, is at the expense of you having to do the "authenticate + install" dance again after you login! So I had to create an onboarding step, kind of to explain to the user the different steps he has to take.
It's when you first start the app it asks you to login using GitHub before you see anything else.
cmux desktop app currently requires signing in to GitHub. We will build out better support for local repositories and remove sign in requirement soon.
It’s an interesting direction, but feels pretty expensive for what might still be a guess at what matters.
I’m not sure an LLM can really capture project-specific context yet from a single PR diff.
Honestly, a simple data-driven heatmap showing which parts of the code change most often or correlate with past bugs would probably give reviewers more trustworthy signals.
This is not that expensive with Gemini, they give free keys that have plenty of req/day, you can upload your diff + a bundle of the relevant part of the codebase and get this behavior for free, at least for a small team with ~10-20 PR's / day. If you could run this with personal keys, anyhow.
Might just be me, but I understood "expensive" in terms of raw computation necessary to get the answer. Some things aren't really worth computing, even if it's someone else footing the bill.
Premise is amazing. Wonder if there are tools that do something similar by looking at diff entropy.
Yeah this is honestly pretty expensive to run today.
> I’m not sure an LLM can really capture project-specific context yet from a single PR diff.
We had an even more expensive approach that cloned the repo into a VM and prompted codex to explore the codebase and run code before returning the heatmap data structure. Decided against it for now due to latency and cost, but I think we'll revisit it to help the LLM get project context.
Distillation should help a bit with cost, but I haven't experimented enough to have a definitive answer. Excited to play around with it though!
> which parts of the code change most often or correlate with past bugs
I can think of a way to do the correlation that would require LLMs. Maybe I'm missing a simpler approach? But agree that conditioning on past bugs would be great
Gemini is better than GPT5 variants for large context. Also, agents tend to be bad at gathering an optimal context set. The best approach is to intelligently select from the codebase to generate a "covering set" of everything touched in the PR, make a bundle, and fire it off at Gemini as a one shot. Because of caching, you can even fire off multiple queries to Gemini instructing it to evaluate the PR from different perspectives for cheap.
Yeah, adding a context gathering step is a good idea. Our original approach used codex cli in a VM, so context gathering was pretty comprehensive. We switched to a more naive approach due to latency, but having a step using a smaller model (like SWE-grep) could be a nice tradeoff.
For the correlation idea, you might take a look at how Sentry does it, they rely mostly on stack traces, error messages, and pattern matching to map issues back to code areas. It’s cheap, scalable, and doesn’t need an LLM in the loop, which could be a good baseline before layering anything heavier on top.
As for interactive reviews, one workflow I’ve found surprisingly useful is letting Claude Code simulate a conversation between two developers pair-programming through the PR. It’s not perfect, but in practice the dialogue and clarifying questions it generates often give me more insight than a single shot LLM summary. You might find it an interesting pattern to experiment with once you revisit the more context-aware approaches.
> Honestly, a simple data-driven heatmap showing which parts of the code change most often or correlate with past bugs would probably give reviewers more trustworthy signals.
At first I thought this to but now I doubt that's a good heuristic. That's probably where people would be careful and/or look anyway. If I were to guess, regressions are less likely to occur in "hotspots".
But this is just a hunch. There are tons of well reviewed and bug reported open source projects, would be interesting if someone tested it.
A large portion of the lines of code I'm considering when I review a PR are not part of the diff. This has to be a common experience - think of how often you want to comment on a line of code or file that just isn't in the PR. It happens almost every PR for me. They materialize as lose comments, or comments on a line like "Not this line per-se but what about XYZ?" Or "you replaced this 3 places but I actually found 2 more it should be applied to."
I mean these tools are fine. But let's be on the same page that they can only address a sub-class of problems.
> https://0github.com/stack-auth/stack-auth/pull/988
Very fun to see my own PR on Hacker News!
This looks great. I'm probably gonna keep the threshold set to 0%, so a bit more gradient variety could be nice. Red-yellow-green maybe?
Also, can I use this on AI-generated code before creating a PR somehow? I find myself spending a lot of time reviewing Codex and Claude Code edits in my IDE.
Yeah we definitely want to make the gradient and colors configurable.
What form factor would make the most sense for you? Maybe a a cli command that renders the diff in cli or html?
colorbrewer has proven high contrast gradients and also color blind options.
a cli command with two options, console (color) and HTML opens all doors, right?
Either would work, I think. How I do it right now is that I let AI edit automatically, but then check the diff in Cursor before I stage my Git changes. May be different for others.
Yeah, heatmapping the diff before creating a PR would need tighter IDE integration. We're working on cmux for this purpose. It's kinda an IDE, and it lives in the same repo: https://github.com/manaflow-ai/cmux.
After we add the heatmap diff viewer into cmux, I expect that I'll be spending most of my time in between the heatmap diff and a browser preview: https://github.com/manaflow-ai/cmux/raw/main/docs/assets/cmu...
Perhaps more time that you would spend writing code yourself.
You’re not going to be able to keep the domain name 0github.com for too long. I’d suggest you start finding a new one immediately.
why?
Because it violates GitHub’s trademark. I expect them to send the author a cease and desist notice; and if the author is unresponsive or challenges the notice, GitHub will almost certainly initiate the dispute (UDRP) process, which will inevitably cede control of it to them.
For the same reason your diff viewer highlights it: it looks like a scam attempt, not like a clever pun.
You likely will be able to keep it without trouble, but many corporate security systems would flag it.
I think the need for such a tool should be avoided by simply making reasonable PRs. And what's ironic is that I now have to review PRs written by a no-code person using AI tools. They even response to my comments using AI as well. And with this tool it becomes even more absurd. I guess next step is to replace the reviewer with another AI tool.
I tried it on a low-complexity Rust PR I worked on a few months back and it did a pretty good job. I'd probably change where the highlights live (for example x.y.z() -> x.w.z() should highlight y/w in a lot of cases).
For the most part, it seems to draw the eye to the general area where you need to look closer. It found a near-invisible typo in a coworker's PR which was kind of interesting as well.
https://0github.com/geldata/gel-rust/pull/530
It seems to flag _some_ deletions as needing attention, but I feel like a lot of them are ignored.
Is this using some sort of measure of distance between the expected token in this position vs the actual token?
EDIT: Oh, I guess it's just an LLM prompt? I would be interested to see an approach where the expected token vs actual token generates a heatmap.
Happy to hear!
> Is this using some sort of measure of distance between the expected token in this position vs the actual token?
The main implementation is in this file: https://github.com/manaflow-ai/cmux/blob/main/apps/www/lib/s...
EDIT: yeah it's just a LLM prompt haha
Just a simple prompt right now, but I think we could try an approach where we directly see which tokens might be hallucinated. Gonna try to find the paper for this idea. Might be kinda analogous to the "distance between the expected token in this position vs the actual token."
This is very cool and I could see it being really useful especially for those giant PRs. I'd prefer it if instead of the slider I could just click the different heatmap colors and if they indicated what exactly they were for (label not threshold). I get the underlying premise but at a glance it's more to process unless I was to end up using this constantly.
Currently tooltips are shown when hovering on highlighted words. Need to make it visible on mobile though. Was wondering if you were thinking of another way to show the labels besides hovering?
I was referring to something more akin to a legend like you have in the examples "(examples: hard-coded secret, weird crypto mode, gnarly logic)." where I could click "hard-coded secret" (not the best label but you get the idea) and it would filter on those instead of the slider.
You should have clear metrics, not ChatGPT. ChatGPT is not trained on a huge dataset related to this task.
This is something I have found missing in my current workflow when reviewing PR's. Particularly in the age of large AI generated PR's.
I think most reviewers do this to some degree by looking at points of interest. It'd be cool if this could look at your prior reviews and try to learn your style.
Is this the correct commit to look at? https://github.com/manaflow-ai/cmux/commit/661ea617d7b1fd392...
https://github.com/manaflow-ai/cmux/blob/main/apps/www/lib/s...
This file has most of the logic, the commit you linked to has a bunch of other experiments.
> look at your prior reviews and try to learn your style.
We're really interested in this direction too of maybe setting up a DSPy system to automatically fit reviews to your preferences
Thank you. This is a pretty cool feature that is just scratching the surface of a deep need, so keep at it.
Another perspective where this exact feature would be useful is in security review.
For example - there are many static security analyzers that look for patterns, and they're useful when you break a clearly predefined rule that is well known.
However, there are situations that static tools miss, but a highlight tool like this could help bring a reviewer's eyes to a high risk "area". I.e. scrutinize this code more because it deals with user input information and there is the chance of SQL injection here, etc.
I think that would be very useful as well.
This is a very interesting idea that we’ll definitely look into.
Maybe add some caching? I clicked one of the example PRs and it kept loading forever...
Shoot, we should have caching in place already. Taking a look now
Getting rate limited by GitHub, gonna add caching here as well. Temporary workaround is to sign in manually and return to example page: https://0github.com/handler/sign-in
pushed a fix, should work now
Can someone please explain to me how do people build these kind of tools? My background is classic Java/C# backend development and SQL. A bit microservice using Spring Boot. Its 8:30pm and I'm watching React tutorials to understand better how modern websites are built - e.g. use useState, useRef etc.
Now, how does any of my experience translate to building tools like cmux? I genuinely want to understand how.
Is the answer to go line by line of cmux code base or make an attempt to open a PR on one of the bugs issues on cmux and, by magic and time, I will eventually understand?
Your experience in coding is enough, you need more practice in "problem solving" with crazy ideas and working through them to the finish line.
Besides, this is just a thin layer on an LLM, with questionable actual quality. Learn to do the real work, no magic machine can take learning and skill building off your shoulders.
If your goal is to make something useful, I think the fastest way is probably to build a CLI only version since you can theoretically render heatmaps and make a task manager in a CLI form factor. And your background in Java/C# helps here.
Use Claude Code or Codex for everything, learn how to prompt well. >90% of cmux and 0github.com was written by LLMs. Most of it was just me asking the LLM to implement something, testing it to see if it works, and if it doesn't, I'll ask the LLM to write logs, and I'll paste the logs back to the LLM. Ask gpt-5-pro for architecture choices, like what tech/dependencies to use.
But if your goal is to learn React, I'd recommend going through the official getting started documentation, it's pretty good.
High level: hit github api, feed code to llm, display results in web app.
If you want to learn web apps start with the docs, eg. Official react docs or even just learning vanilla JavaScript if you don’t know it.
Start with little pieces like hitting the github API and displaying some json in the terminal
You could also just start prompting an llm to scaffold a project for you and then trying to debug whatever issues come up (and they will)
What would you recommend to someone new in your team who had only ever used python and a bit of SQL, and had never touched Java or Spring Boot?
This is really useful. Might want to add a checkbox at a certain threshold, so that reviewers explicitly answer the concerns of the LLM. Also you can start collecting stats on how "easy to review" PR's of team members are, e.g. they'd probably get a better score if they address the concerns in the comments already.
I like the idea!
File `apps/client/electron/main/proxy-routing.ts` line 63
Adding a comment to explain why the downgrade is done would have resulted in not raising the issue?
Also two suggestions on the UI
- anchors on lines
- anchors on files and ability to copy a filename easily
Good suggestions! Will make it more URL friendly.
> Adding a comment to explain why the downgrade is done would have resulted in not raising the issue?
Trying it out here with a new PR on same branch: https://0github.com/manaflow-ai/cmux/pull/809
Will check back on it later!
EDIT: seems like my comment online 62 got highlighted. Maybe we should surface the ability edit the prompt.
Thanks for the test!
Thinking about it with the feedback, I'm not sure of what I would have liked to see actually.
First I was expecting no highlight once you added a comment explaining why.
But then, seeing the highlight, I'm thinking that a comment shouldn't a magical tool to allow doing crazy stuff.
I don't know anything about the Electron wrapper, so maybe it is actually possible to do HTTPS and someone could point out how to achieve this. And having the downgrade highlighted can help having this someone finding out.
I'll keep thinking about it! Thanks!
I think this "'should review' threshold" is a really great idea, but I probably wouldn't be able to trust it enough to make it useful.
This makes reading long PRs not instantly LGTM… now the heatmap guides my eyes so I know where to look.
This is cool! Please add a dark theme and respect `prefers-color-scheme: dark` :)
Very, very useful. I'll give it a try. Thanks for sharing!
Change the domain name, you will likely get a cease and desist otherwise.
I feel like this is really smart. Going to have to set it up!
Just prepend 0 in front of github in your PR link and it should work
Ah, I see now.
wondering what if you run a SAST (a fast one) and share that with codex alongside the code diff?
yoooooo this looks awesome!
Reminds me of this one, highlighting for text https://github.com/mattneary/salience
How do I opt out of this tool? I do not want anyone reviewing my code or projects to use or engage with it and it is explicitly against the TOS of those projects. It would be nice if this tool screened for a robots.txt or something of the sort so that I could ensure that this tool never touches my projects.
Don't share your code publicly then?
