I agree with the general sentiment here that this is the future of coding for a lot of tasks. But in terms of a business case for your product I'm really struggling to see how this beats Claude code action? Which integrates directly with GitHub, at no additional cost, and I can use an oauth token to use my subscription.
Hey Ishaan here (co-founder), totally fair point, claude code actions are great for GitHub workflows. We see Omnara fitting in when you want to keep a live session going across devices (terminal ↔ web ↔ mobile) and outside GitHub too
I see, thanks for explaining and congrats on the launch! After re-reading the description, the ability to use other frameworks might become a USP too.
Just a random remark, what's annoying and a pain point in my workflow are definitely proper development environments for agents . Not just runtimes but also managing secrets etc. Maybe an avenue to explore and use in marketing copy.
Haven't used Windsurf yet, but in other tools this is called 'Agent' mode. So you open up the chat modal to talk to an LLM, then select 'Agent' mode and send your prompt.
Cursor recently lost me as a customer. Too many updates that disturb my workflow and productivity, no easy way to roll back versions, super sparse changelogs, lots of magic in context building, really untransparent pricing on max mode. I recently made the switch to Claude Code on the Max plan and I couldn't be happier. The only real thing I'm missing is the diff view across files, but I assume it's just a matter of time until that's properly implemented in Zed or VSCode.
I feel unstoppable with Claude Code Max. I never thought I'd pay $200 per month for any developer tool, yet here we are, and I also couldn't be happier with it.
Maybe in the US? I will never pay 100$ for a subscription and I despise that people normalized it by even buying this stuff instead of saying "no, that's way too expensive".
Well bucko it’s time to open your wallet. There’s creatives out there who spend at least $1000/month in subscriptions for tools, but without those tools they could never do most of the work they do. And some who buy physical gear like photographs and videographers pay even way more than that for equipment.
Soon it will be the same for developers. Developers really are a spoiled bunch when it comes to paying for things, many will balk at paying $99/year just to publish stuff on an App Store. Everyone just wants free open source stuff. As expectations on developer productivity rises, you will be paying for these AI tools no matter how expensive they get, or you will just be gentrified out of the industry. The choice is yours.
I work in a cleanroom to fabricate semiconductor devices and I spend hundreds of euros per hour to use specific tools which mostly just use electricity and maintenance. Should we complain that it’s too expensive or should we use them because they’re worth the price?
Things have a price for a reason. It’s up to you whether it’s worth paying that or not.
We are talking about personal use and then people don't pay for it out of their own pocket but the company's. At least I hope so because otherwise it would be very dumb.
I’m also talking about personal use. These are research devices for my PhD. I’m obviously not paying out of pocket, but my funding agency does.
I’m trying to convey that if a tool increases your efficiency by more than it costs then it’s worth paying for it regardless of how expensive it is. It’s how the economy works.
There is no free lunch. Even if a company pays for it instead of you, their LLM costs per developer will be factored in to what they are willing to provide as compensation. So one way or another, the end result is you get paid for less for the same amount of work today.
That “if” doesn’t apply to all of us, though. Not everybody is paid by the hour. I’d love to try something like Claude code, but $100 per month is way too expensive for me, and it probably wouldn’t even give me a single extra dollar of income. I think I’ll just wait for the time when local LLMs will be good enough to be a viable alternative.
By the time you can run good enough local LLMs without splurging on sufficiently powerful hardware, those LLMs will look like toys compared to whatever cloud based LLMs are available.
That's a great question. Probably not. IDK. I'm also only paying this much to maintain momentum on a personal project. I also know in a year, these LLM products will change drastically, pricing tiers will transform, etc.. So I can't predict what will happen in a year but things will probably be cheaper.
Edit: On the other hand, the state of the art tools will also be much better in a year, so might keep that high price point!
Am I rationalizing my purchase? Possibly. If I'm not using it daily, I will cancel it, I promise :)
I think there is definitely room to price AI tools way higher. Developers are being slowly boiled like frogs right now. Getting addicted to AI tools to the point they can’t work without them, that’s when you raise the price.
I see it as an investment into my future. I was able to make progress on a personal project with Claude Code which I failed at using other tools. Yes, I will, and apparently have, paid multiple hundreds of dollars to get the project release ready. But I definitely need to keep in mind that I'm not going to at that velocity all the time, which would make the $200 price point not justifiable long term.
I just started with it, so still getting my feet wet, but it's been better than any other tool at really grokking my codebase and understanding my intent. The workflow feels better than a strict IDE integration, but it does get pricey really quickly, and you pretty much need at least the $100 Max subscription.
Luckily, it should be coming with the regular $20 Pro subscription in the near future, so it should be easier to demo and get a feel for it without having to jump in all the way.
The current max pricing is actually as transparent as it has ever been: It's 20% more to use Max than the APIs directly. I am not sure if your feedback is outdated/based on a previous version of reality?
I have a workflow that also uses micro commits.
I keep my older JetBrains IDE open at the same time.
Using feature branches liberally, any successful interaction between me and the LLM in Cursor results in a micro commit. I use the Cursor AI ‘generate commit message’ for speed.
Every so often, I switch over to Jetbrains to use Git Interactive Rebase to tidy up the commits, as the diff viewer is unsurpassed. Then those micro commits get renamed, reordered, squash merged as required. All possible from Git CLI of course, but the Jetbrains Git experience is fantastic IMHO. All their free community edition IDEs have this.
Personally, I've been using Cursor since day 1. Lately with Gemini 2.5 Pro. I've also started experimenting with Zed and local models served via ollama in the last couple of days. Unfortunately, without good results so far.
Say I'm chatting in a git project directory `undici`. I can show you a few ways how I work with codex.
1. Follow up with Codex.
`mct "fix bad response on h2 server" --model anthropic/claude-3.7-sonnet:thinking`
Machtiani will stream the answer, then also apply git patches suggested in the convo automatically.
Then I could follow up with codex.
`codex "See unstaged git changes. Run tests to make sure it works and fix and problems with the changes if necessary."
2. Codex and MCT together
`codex "$(mct 'fix bad response on h2 server' --model deepseek/deepseek-r1 --mode answer-only)"`
In this case codex will dutifully implement the suggested changes of codex, saving tokens and time.
The key for the second example is `--mode answer-only`. Without this flagged argument, mct will itself try and apply patches. But in this case codex will do it as mct withholds the patches with the aforementioned flagged arg.
3. Refer codex to the chat.
Say you did this
`mct "fix bad response on h2 server" --model gpt-4o-mini --mode chat`
Here, I used `--mode chat`, which tells mct to stream the answer and save the chat convo, but not to apply git changes (differrent than --mode answer-only).
You'll see mct will printout that something like
`Response saved to .machtiani/chat/fix_bad_server_resonse.md`
Now you can just tell codex.
`codex "See .machtiani/chat/fix_bad_server_resonse.md, and do this or that...."`
*Conclusion*
The example concepts should cover day-to-day use cases. There are other exciting workflows, but I should really post a video on that. You could do anything with unix philosophy!
Really interesting method. I've been calling a similar strategy the library effect. Whenever I work in an environment where other people are productive (or at least look productive) I can focus much better and get in the zone. It's now gotten to a point where I'm actively seeking desks with my screen exposed to the room, so people would be able to see me procrastinate, guilt tripping me to limit this sort of behavior.
This used to work for me, but not anymore. The less I care about what other people think the more I don’t care about procrastinating even when they’re right next to me.
> Really interesting method. I've been calling a similar strategy the library effect
As libraries reinvent themselves for an era where all the world’s knowledge is available on my cell phone, I wish more emphasis was placed on meeting booths.
Because then I’d work from them all day and never consider coworking spaces.
> It's now gotten to a point where I'm actively seeking desks with my screen exposed to the room, so people would be able to see me procrastinate, guilt tripping me to limit this sort of behavior.
I have this same brain. Working in public at a coffee shop is a great baseline, but it's even better if I can feel the social pressure to not fuck off even if it's made up by my own neurotic head. It's a crazy double-edged sword to wield. Really useful, but I think it heightens burnout and I can't stand to stay in the same place for long due to the palpable buildup of pressure to Go Home.
I recently tried to implement a workflow automation using similar frameworks that were playwright or puppeteer based. My goal was to log into a bunch of vendor backends and extract values for reporting (no APIs available). What stopped me entirely were websites that implemented an invisible captcha. They can detect a playwright instance by how it interacts with the DOM. Pretty frustrating, but I can totally see this becoming a standard as crawling and scraping is getting out of control.
Thanks so much! Yes, a lot of antibots are able to detect Playwright based on browser config. Generally, antibots are a good thing -- I think in the future, as web agents become more popular, I'd imagine a fruitful partnership to prevent misuse if it's coming from a trusted web agent v. an unknown one
It depends on what your setup looks like. If your using tailwind and a headless component library like radix or shadcn. LLMs can provide you with pretty decent looking layouts from very simple prompts. If your using plain CSS outputs can vary widely in quality, at least from my own experience.
