YHK - yet another hacker news clone

147 points kmansm27 4 days ago 158 comments

Hey y’all, Kartik, Ishaan, and Christian from Omnara (https://www.omnara.com/) here. We’re building a web and mobile agentic IDE for Claude Code and Codex that lets you run and interact with coding agents from anywhere. Omnara lets you run Claude Code and Codex sessions on your own machine, and exposes those sessions through a web and mobile interface so you can stay involved even when you’re away from your desk. Think of it like Claude Code Desktop or Conductor, except you can continue your sessions on your phone.

Here’s a demo of the web and mobile apps - https://youtu.be/R8Wmy4FLbhQ

We started using Claude Code early last year and quickly ran into a pattern: agents could work for long stretches on their own, but progress would stall whenever they needed follow-up input. If that happened while we were away from our desks, everything just paused. We looked at remote agent solutions like Codex Web and Devin, which were the main options at the time, but they ran in remote VMs, and we wanted our coding agent to run in our own environment. Our first attempt at solving this was a lightweight wrapper that streamed messages from the Claude Code CLI to a mobile app, but that approach ended up being fragile and hard to maintain.

As the Claude Agent SDK matured, it gave us enough control to rewrite Omnara from scratch and run the agent loop directly. We chose to build a GUI across web and mobile instead of a TUI or CLI, because we think GUIs are generally more ergonomic for working with agents and code, especially on mobile. We still preserve the main strength of CLIs and TUIs: running anywhere, including on headless machines.

Omnara keeps that property by running a small headless daemon on the user’s machine (or a remote VM) that hosts the agent loop. The daemon maintains an authenticated, outbound WebSocket connection to our server, which relays messages between the agent running on the user’s machine and any connected web or mobile clients. Because the daemon only makes outbound connections, there’s no need for exposed ports, SSH access, or tunneling on the user’s machine.

In our first version of Omnara, users liked that agent sessions ran in their own environment, but they still depended on the machine staying online. Some users ran Omnara on a remote machine that stayed up, which worked well for them, though most still did most of their work on laptops. In the current version, Omnara can continue an agent session in a hosted remote sandbox when your local machine goes offline.

The conversation state of an agent is already persisted on our server, and you can optionally enable cloud syncing for the working code. When syncing is enabled, Omnara creates git commits at each turn in the conversation and pushes them to our server, so execution can resume from the same state regardless of whether it continues locally or in the cloud. If you continue working in a remote sandbox, you can later pull any changes back into your local environment when you return to your machine. Environment parity in the sandbox isn’t perfect yet, but in practice, missing dependencies are usually easy to resolve by asking the agent to install them.

Another thing we learned from using the initial version of Omnara is that mobile is fine for quick interactions, but not great for extended back-and-forth. Users asked for a hands-free way to keep agents moving while walking, driving, or doing something else, which led us to add a voice agent. Coming from more traditional software engineering backgrounds, we honestly thought coding by talking to a voice agent would be gimmicky and added it mostly as a fallback.

What surprised us is how useful the voice agent ended up being in practice. When working with coding agents, being redundant and overly explicit usually helps, and people naturally give more detail when speaking than when typing. Going back and forth with the agent as the conversation unfolds tends to produce a much more solid plan than trying to one-shot it with a prompt (this could technically also be done over text, but talking and iterating over voice feels easier and more natural). It’s also just fun. Talking through an idea with an agent while out on a walk is a lot more enjoyable than staring at a terminal screen.

To try it out, open your terminal and download Omnara with

  curl -fsSL https://omnara.com/install/install.sh | bash
then run omnara inside any git repository. This starts a headless Claude Code or Codex session in that repo, which immediately appears in the Omnara web and mobile apps. From there, you can continue that session or start new ones remotely (with or without worktrees) and switch between the web and mobile clients without interrupting the agent.

Omnara is free for 10 agent sessions per month, then $20/month for unlimited sessions. When agents run in your own environment, you can use your existing Claude or Codex subscription, so there’s no need to pay us for additional tokens. If you use Claude Code or Codex, we’d love to hear your feedback on Omnara!

zomglings 4 days ago | parent

I have been hungry to do more work from my cell phone. It's ridiculous to be forced to sit in front of a computer to work with AI.

My current solution is to have claude (--dangerously-skip-permissions) listen for messages in my slack DMs to myself and take action in response to those messages.

I would happily switch to something better.

Why is Omnara better?

kmansm27 4 days ago | parent

There's a lot of solutions that people are hacking together to be able to use coding agents from their phone (e.g. terminal emulator + tailscale, slack, whatsapp, telegram). I enjoy Omnara more than those solutions because it's a native experience tailored for coding agents, e.g. you can select models/harnesses, spin up new sessions, create worktrees, view code changes, see tool calls, have live previews, have voice agent support, and on and on. Omnara is a solution meant to interact with coding agents from your phone, so we're able to add a lot of nice UX features to our app that those other solutions can't.

devinbernosky 4 days ago | parent

OpenCode is free and has an excellent front end for this kind of work

cmsparks 4 days ago | parent

OpenCode is great and `opencode serve` in particular is very cool. Though I think the main thing is that you need to manage the OpenCode server yourself and expose it via tailscale or something like that. Our goal is to provide managed infrastructure around the coding agent harness with features like mobile, sandboxes, preview urls, etc.

Our goal is to be harness agnostic as well, so eventually we will be adding support for running OpenCode sessions in Omnara.

qwesr123 4 days ago | parent

How do you plan to be harness agnostic if you design requires using the agent SDKs (Claude Agent SDK, etc.)?

cmsparks 3 days ago | parent

When I say harness agnostic, I more mean we're agnostic to what harness is running, sort of like Zed with ACP: https://agentclientprotocol.com/overview/introduction. It still necessitates bringing the SDK and us writing an adapter for the SDK, but you still get to use the same chat interface for all the agent SDKs.

eclipxe 4 days ago | parent

OpenChamber is a good option you use opencode

cmsparks 4 days ago | parent

FWIW, we'll definitely add OpenCode support soon!

gdilla 4 days ago | parent

sounds really close to fart, in japanese.

kmansm27 4 days ago | parent

Omnara is used while on the toilet a lot

ncphillips 4 days ago | parent

I don't quite see the appeal, because Claude Code already supports something similar. They spin up container to make the changes in and then open a PR. I can just use the Claude iOS app to do this. My computer doesn't need to be running or exposed to the internet.

kmansm27 4 days ago | parent

Omnara’s is useful if you have a complex dev setup that’s hard to replicate in Claude’s remote container, or you want to test things out locally without any friction. Omnara tries to make switching between being on your computer and being on your phone feel seamless, whereas in Claude, local and remote dev feel more disconnected.

fragmede 4 days ago | parent

I can't sit back down at my computer and cd/ssh/tmux into that same environment.

p-a_58213 4 days ago | parent

I think someone should also mention Happy (https://happy.engineering), which has decent mobile clients and is currently MIT-licensed.

Although I must say that Omnara's UI looks absolutely fantastic. Well done!

faramarz 4 days ago | parent

I use this everyday, and even have the Happy server on my home Mac to skip the cloud relay.

I think I will only explore an alternative if the UI on the mobile is dramatically better (something to explore) but im trying my best to only pay for the model these day and avoid any other tooling subscription, and doing pretty great thus far.

isehgal 4 days ago | parent

Totally get it, we're trying to minimize subscriptions too. Free tier gives you 10 sessions/month with no length limits, so you can actually get a decent amount done before deciding if it's worth paying

faramarz 4 days ago | parent

Just watched your walkthrough video and have to say kudos, that looks like a really tight release. will give it proper test drive.

cheers and congrats on the launch!

isehgal 4 days ago | parent

Thanks for the shout! Happy looks solid - always great to see more options here. Anecdotally from users who've tried both, we've heard Omnara has better reliability and latency. We also layer on some features like web support, worktrees, sandboxing, richer git management (diffs, checkpoints), and preview URLs. Would love to hear what you think if you give it a spin :)

koakuma-chan 4 days ago | parent

So you're just a Claude Code wrapper? Question to YC: how did this get funded?

tverbeure 4 days ago | parent

I used to think that getting admitted to YC was a major accomplishment. Maybe it was at some point, but at the college graduation parties of my daughter it seemed like pretty much everyone who tried had gotten in. Most collapsed after a few months due to infighting, funds mismanagement etc. It was fascinating to watch.

deron12 4 days ago | parent

I think you mean "prestigious" rather than "major accomplishment". You're right, there was a small period of time when it was. However, that window didn't quite align with "best time to do YC" (several years prior to such prestige) nor with "best time to be doing YC" (the prestige embellishes your resume, which is useless if you're otherwise occupied).

It's interesting to me that YC has managed to dilute this prestige to a large extent. I don't think it's an inevitable result of scale: look at Google. I think "Xoogler" prestige has diminished, but it's not nearly as bad as what has happened to the YC label.

My theory is: YC never figured out their formula. The whole formula is essentially Paul Graham, who had a knack for trusting his gut (and sometimes his wife) when everything else in his "system" was saying NO.

Once they lost that, they had to rely on what was left, and it simply wasn't competitive anymore. It's like Apple in their John Sculley era. While Sculley is credited with growing Apple's revenue from $800 million to $8 billion, his approach created a "mess of dull SKUs" that eventually confused customers and diluted the brand.

They also have a (bad) habit of removing access to bookface for all the founders who aren't "active", decimating their network and in some ways discarding valuable knowledge around what didn't work.

geoffschmidt 4 days ago | parent

I think Jessica Livingston deserves at least as much credit as Paul for YC's success in that early era, and IIRC he has the same view.

kmansm27 4 days ago | parent

We're a very complex Claude Code wrapper :) Try it out and lmk what you think!

koakuma-chan 4 days ago | parent

I like your landing page and the video where the guy does stuff outside while his agents work in background, but the nature of your company does not appear to me as being consistent with screenshots of messages from Paul Graham discussing what startups ought to be like, etc, that YCombinator's LinkedIn account keeps posting. I'm not saying that this is you, but I have an impression that a lot of these companies getting into YC do it as a money grab and/or for bragging rights while being as technically sophisticated as an above-average high school project. It's great that you got funded, but I'm not sure if you should have been.

kmansm27 4 days ago | parent

I'd say to try it out first, and then let me know what you think! And a product doesn't have to be technically sophisticated to be funded by YC (although I would say that Omnara is a pretty technical product, which you'll see if you try it out)!

dbbk 4 days ago | parent

YC funded a brainrot IDE. They will literally throw money at anything. They don’t care.

keepamovin 4 days ago | parent

There's certainly something to the "mass delegation" trend. My best rn is on email: https://ai-chat.email

cmsparks 4 days ago | parent

Yeah we've definitely taken some inspiration from everyone who building an agent orchestrator/delegation app right now!

notabot33 4 days ago | parent

Another option that does all this and more for open code: https://github.com/btriapitsyn/openchamber

Not affiliated with that project, but have been using it for a few weeks and it blows every other 'GUI for the CLI agents' I've tried out of the water in terms of both features and just working snappily/consistently.

Also totally free, and actively being improved by the solo maintainer and an active community of contributors.

Omnara providing a tunnel for you is nice, but considering Tailscale is dead simple and free, feels hard to justify $20 a month for what looks like considerably less features than openchamber

kmansm27 4 days ago | parent

Yeah, this looks great for OpenCode (which we're planning on adding soon!), but I personally have Claude Code and Codex subscriptions, which Omnara supports. We also support syncing your local session to a cloud sandbox to continue your session, and in the cloud sandbox, we provide LLM tokens. As well as our voice agent costs are covered by us.

notabot33 4 days ago | parent

thanks I missed "support syncing your local session to a cloud sandbox to continue your session" when reading through your docs that's a really nice best of both worlds feature!

FYI openchamber/opencode support claude/codex/copilot subscriptions as well

sanufar 4 days ago | parent

Woah, I had this exact idea, down to the tunneling and local machine! I basically just coded up a Tailscale + caffeinate harness for my agents and it's been working super well. Your UI looks great though, glad to see more players in this space!

sanufar 4 days ago | parent

Also your promo video is really fun! https://www.omnara.com/assets/landing/video/movie.mp4

kmansm27 4 days ago | parent

Haha thanks! It was fun to shoot :)

jdmoreira 4 days ago | parent

If you can see the messages unfortunately thats a deal breaker for me. If its encrypted end-to-end than I’m in.

isehgal 4 days ago | parent

Fair concern. We don't have true E2EE yet because our service needs access to message content for cross-device sync, notifications, and agent execution. Everything is encrypted in transit and at rest, and all repo operations happen locally on your machine.

We've heard this from other users and it's on our roadmap. The challenge is we're building features like voice coding agents and hosted sandboxes that require plaintext inputs, so we'd need two execution models. Doable, but adds complexity for our team size.

That said, it's something we're prioritizing as we grow. No promises on timing, but it's coming.

If you want to discuss specific requirements or a local-only mode, happy to chat: https://discord.gg/Dc46sYk6e3

kovek 4 days ago | parent

https://happy.engineering/ says that they have E2E encryption. Is that true?

kmansm27 4 days ago | parent

Yes, they have E2EE, but it comes with some limitations in the features they're able to provide.

kovek 4 days ago | parent

Like what? I like it a lot...

kmansm27 4 days ago | parent

Two of the main feature's we're investing heavily into are remote sandboxes + syncing, and voice agent support, wouldn't work with E2EE.

kovek 4 days ago | parent

I can voice chat with Happy coder. Also, I run happy coder in a sandbox of mine on my computer. What do you mean by syncing? Happy coder syncs sessions between all my happy coder clients. I can even see in real time how happy coder in my browser's conversations progress as well as on my phone, in parallel.

splintercell 3 days ago | parent

Happy is an abandonedware unfortunately. It's a great app and dev can capitalize a lot from it but for some reason he hasn't been seen or heard in months since the last release.

There are attempts to create a fork maintained by other developers, but they're yet to be launched.

kmansm27 4 days ago | parent

Replying to your latest comment here:

What do you mean by syncing? Happy coder syncs sessions between all my happy coder clients. I can even see in real time how happy coder in my browser's conversations progress as well as on my phone, in parallel.

Omnara also displays realtime conversations between all Omnara clients. What I mean by syncing is syncing your conversation and code changes to a cloud sandbox, which is useful if you're using Omnara on your laptop and you close your computer (as explained in the original post). If you run your agents on a persistent cloud VM, then this is less of a value add.

I can voice chat with Happy coder.

We use https://docs.livekit.io/agents/ which runs the voice agent in the cloud (to enable the above use case, and a better experience when you're using your phone when it's off), whereas I believe happy runs a client-side voice agent.

kovek 4 days ago | parent

Thanks for answering my questions! I see that Happy Coder is not far from Omnara. I hope Omnara can be not too far from E2E encryption. The lack of E2E encryption was why I didn't chose Omnara.

sneak 4 days ago | parent

> We don't have true E2EE yet because our service needs access to message content

That means you don't have E2EE, period. Implying that there is such a thing as "true E2EE" (as opposed to "E2EE") either indicates that you don't know what E2EE means, or that you're scammily trying to do what Apple does with iMessage and say that something that isn't E2EE is, for marketing purposes.

E2EE means that nobody except the endpoints has keys. There is no such thing as "true E2EE" any more than there is such a thing as "true pregnancy".

unsupp0rted 4 days ago | parent

Hysterical E2EE

kmansm27 3 days ago | parent

Yep, you're right, we don't have E2EE period (and we don't claim to have it anywhere), for the reasons I mention above (our cloud sandbox agent and voice agent need plaintext messages, so we'd need access to the keys, which defeats the purpose of E2EE). Apologies for the incorrect wording!

lalo2302 4 days ago | parent

Feels expensive for something that an engineer can hack in a couple of ours with tailscale and Claude Code. Has potential though. At $9 I'd be totally in, but moving from CC's Max plan at $100, adding $20 makes me wanna just hack an alternative. Maybe I'm just cheap.

redrove 4 days ago | parent

Agreed. In a post-CC world anyone can build this for themselves so easily. Especially since their entire supposed customer base already uses these tools to begin with.

kmansm27 4 days ago | parent

Yeah that makes sense. I personally feel like the tailscale + terminal emulator solution is pretty limited compared to Omnara's interface, and there's also 0 hassle of maintaining anything on your own with Omnara. You can try out Omnara for free, and see if you like it before paying! 10 sessions can get you pretty far, and there's no limit on the session length.

lalo2302 4 days ago | parent

I dug on the product a bit further and it seems it includes remote sandboxes? Then I understand the pricing, it makes sense.

At a first glance I understood all sessions would be created at the local machine. My niche use case having a mac mini on 24/7 at home would make this interesting. That’s why I mentioned the cheaper price.

Looks like a good product. Everyone is afraid of the grind, keep going!

GraffitiTim 4 days ago | parent

Funny how similar this is to the famous comment on Dropbox's Launch HN post in 2007.

"1. For a Linux user, you can already build such a system yourself quite trivially by getting an FTP account, mounting it locally with curlftpfs, and then using SVN or CVS on the mounted filesystem. From Windows or Mac, this FTP account could be accessed through built-in software."

blahblahson 4 days ago | parent

Drop Box is free though.

cmsparks 4 days ago | parent

they're free up to a limit, just like us!

gverrilla 3 days ago | parent

I migrated away from dropbox to seafile. 2gb free plan to now unlimited =) total: 3 hours with claude code.

koakuma-chan 4 days ago | parent

Why is it funny? Is Dropbox supposed to be some kind of success? Their stock is down -16.72% from IPO seven years ago.

mfkp 4 days ago | parent

Yeah, it's only at a 6.355B market cap, complete failure!

saberience 4 days ago | parent

You couldn't vibe-code Dropbox in an hour though...

actionfromafar 4 days ago | parent

You wouldn’t vibe-code a car...

gregjw 4 days ago | parent

hmm, i wonder how long it would take nowadays actually

ywvcbk 3 days ago | parent

Exception in those days it took a lot of time and effort to build software and you couldn't just do it by answering a few multi choice questions on a phone.

tomasphan 3 days ago | parent

Dropbox is not a tool solely for developers though.

ciaranmca 4 days ago | parent

True, certainly something you could do with Tailscale+tmux but if this makes that a lot easier then it could end up being popular, increasingly the people who are pushing the most money into the likes of Anthropic are not rhe people focusing too much on the amount of money being put towards achieving their goal, rather the progress(tbh more realistic to say perceived progress) towards that goal in the shortest amount of time.

Obligatory https://news.ycombinator.com/item?id=9224

fragmede 4 days ago | parent

You are cheap! So am I! We're developers. Just ask Claude to use the Claude chrome extension MCP and have it setup Tailscale for you. Not to be rude, but we as developers have to learn not to smell our own farts and think they're gold. I had Claude shit out a shell script that's useful for me, and for people like me, but holy hell, that does not a startup charging $20/month make.

Welcome to the new economy.

busch_j 3 days ago | parent

Facts, I have built something myself doing this (granted I am a software eng) and pretty much anyone with claude code / codex could do it in a couple hours and you can tailor it to your exact workflow.

The apps that do this are an easy money grab though, I have a seen some total trash ones that still rank high on IOS store because people still want this so I am sure they will get some subs.

petervandijck 3 days ago | parent

HN never disappoints!

RobMurray 4 days ago | parent

How does this compare to Happy Coder? https://github.com/slopus/happy

cmsparks 4 days ago | parent

Anecdotally from some Omnara users who have used both, I've heard that reliability and latency when sending messaages is better in Omnara

We try to provide a decent chunk of features on top as well, including (but not limited to):

* web support

* worktrees

* sandboxing

* richer git management (richer diffs, checkpoints, git operations)

* preview URLs

whazor 3 days ago | parent

is there any such manager out there that uses the ACP protocol? (https://agentclientprotocol.com/)

Ideally I would like a ACP proxy wrapper, where I integrate ACP into my code editor and still be able to use it remotely via a phone.

splintercell 3 days ago | parent

I believe Happy has been abandoned. I am a Happy user and I got my wife to also use it. She had a bunch of complaints. She was basically begging me to just start making those changes into Happy source code directly (I even pay money to support Happy), but I believe it's gone. Omnara has a better business model.

kgc 4 days ago | parent

I think the native Claude and Codex apps already do this for free. They even have the voice input.

kmansm27 4 days ago | parent

They currently don't have the ability to use a local session from your phone, and they only have voice input, not voice input and output for completely hands free usage.

CharlesW 4 days ago | parent

> They currently don't have the ability to use a local session from your phone…

Claude Code will help you set this up using tmux. Voice input and output personally seems like a gimmick, but OS accessibilty features should work fine for this.

kmansm27 4 days ago | parent

Voice input + output sounds gimmicky (as I admit in the post), but it's quite useful for mobile coding. It's not as trivial as just printing out whatever Claude Code outputs.

"Claude Code will help you set this up using tmux" - I don't think that you can connect to tmux sessions running in Claude Code/Codex remote VMs using their mobile apps. Their mobile apps don't provide a terminal emulator afaik

CharlesW 4 days ago | parent

> Their mobile apps don't provide a terminal emulator afaik

Right, this requires using a terminal app.

elxr 4 days ago | parent

> Voice input and output personally seems like a gimmick

Nice to have when cooking and I want to use my laptop without wiping my hands dry constantly.

sidsud 4 days ago | parent

I don't really understand the market for handoff of your vibe-coding session. Considering there's a need, does this use-case warrant a full blown SaaS solution?

Sidenote - is this novel enough to be backed by YC? Just seems like a feature that Anthropic/OpenAI could release any day.

kmansm27 4 days ago | parent

The idea is that if agents are coding for you, there's no need to be at your desk to manage them. I think the case for managing coding agents without being at your desk is becoming stronger as agents become more autonomous.

And for your sidenote, we'll see when Anthropic/OpenAI release something similar. For now it's pretty useful, and we're making it better every day.

sidsud 4 days ago | parent

congrats on the launch man! didn't mean to come off negatively. as for the sidenote - it might be worth considering now to push the product forward.

kmansm27 4 days ago | parent

Thanks! And yeah it's definitely something we think about very often, we're coming up with ways to differentiate ourselves.

jpallen 4 days ago | parent

There's a lot of negative feedback in this thread, so let me say I'm really excited to try this! I have caring responsibilities at home that means I'm constantly switching between my laptop and phone. Claude code web has been a very useful tool for this, but it's not a great bit of software. Omnara looks much more configurable and thought out. I've looked for various solutions to this problem that just work, and nothing else mentioned in this thread fits the bill. Your demo looks like it nails it - I'm excited to try!

kmansm27 4 days ago | parent

Thank you! Yeah, a big selling point of Omnara is that it "just works." Let me know how it goes!

jpallen 4 days ago | parent

First impressions are good! Couple of small bits of feedback:

- I only had the option to create a worktree from main. I'd like to be able to pick any starting branch. Not a big deal, I just told claude to checkout the branch I wanted as my first instruction.

- For some reason in the Android app the usual automatic capitalisation of the first letter in a sentence doesn't work. Claude probably doesn't care, but I like to type in proper sentences!

- It would be nice if the worktree names got semantic names, e.g. by running my first prompt through Haiku. Maybe that's not the order things are set up in though

cmsparks 4 days ago | parent

> branching not from main

This is actually a PR that I have open right now, it'll be out soon!

> automatic capitalization

We'll get this fixed

> automatic worktree names

definitely on our roadmap, probably will do that this week

Nextbysam 4 days ago | parent

just use spoq.dev

https://x.com/OafTobarkk/status/2021634083449975125

Nextbysam 4 days ago | parent

great product.

try spoq.dev , it's free

inercia 4 days ago | parent

Open Source alternative: https://github.com/inercia/mitto

TheOnlyWayUp 4 days ago | parent

I see the need and I'll probably give it a go, but how does Omnara handle users' data? Do you store my tokens, stuff about my project, etc.?

If I paste in something confidential, and Omnara suffers a breach tomorrow - will my conversation data be a part of it?

isehgal 4 days ago | parent

Good question. We don't have E2EE yet (it's on the roadmap), so some level of trust in Omnara is required today. All repo operations happen locally on your machine. For messages/chat history: we store those encrypted at rest because we need access to sync across devices, send notifications, and resume agents. Cloud sandboxing is opt-in and would require syncing codebase state.

hmokiguess 4 days ago | parent

How does it compare to https://hapi.run/ ?

I have been pretty satisfied with it, and it’s free with unlimited sessions, so I need a good reason to switch

kmansm27 4 days ago | parent

I haven't tried out https://hapi.run/, but I've tried similar things and in my experience Omnara is much more reliable than the other solutions, as well as I enjoy the UX of Omnara much more. Give it a try, it's one command to set up and the free tier gives you everything that the paid tier does, so you can decide if you like it before paying!

hmokiguess 4 days ago | parent

when you say reliable what do you mean? hapi never once failed for me, it’s self hosted + tailscale so pretty robust

reliability is not big selling point given the high cost on unlimited sessions which I use quite a bunch

kmansm27 4 days ago | parent

I mean messages drop or stall, or syncing doesn't work, or I can't get through setup at all. But I'm sure all these solutions have improved greatly since I've tried them, I tried these things much earlier on. If hapi works perfectly for you, then maybe Omnara wouldn't be much of a value add. Are there any pain points you face with hapi?

hmokiguess 4 days ago | parent

Yeah none of these issues happen to me, so if Omnara has no other value add then I don't see a reason to pay for it.

I was curious if it had something Hapi didn't have, but sounds like it doesn't.

Thanks for your help!

theturtletalks 4 days ago | parent

How is this different from VibeTunnel which is not limited to just Claude and Codex, but brings your terminals with you on your phone using tailscale?

There's also Happy, Coder/Mux, and so many others that actually started out open-source and stayed that way and I can be sure my chats are not going to a 3rd party?

kmansm27 4 days ago | parent

We think that terminal interfaces, especially on mobile, are not going to be the way people end up interacting with agents in the long run, which is a big reason we built Omnara.

And Omnara chats are stored in our DB, which is how we're able to enable our voice agent, cloud syncing, and ability to see all your chats while your machine is offline. Basically anything you see in the web and mobile clients is being proxied/persisted through our server, until you delete the chat.

theturtletalks 4 days ago | parent

Good point, but Happy also has parsers to turn terminal output into "chat bubbles" but with how often Claude Code and Codex change that output, that parser has to be updated every time. With new terminal agents coming into the fray, wouldn't you forever have to parse new agents to make them available?

kmansm27 4 days ago | parent

We use the Claude Agent SDK and the Codex App server, which makes it easier to maintain (we used to parse out the literal terminal when we first launched, which was not maintainable - https://news.ycombinator.com/item?id=44878650). There's also ACP (https://agentclientprotocol.com/get-started/introduction) which we'll probably integrate eventually, which should make it easier to manage all the harnesses.

dakolli 4 days ago | parent

Its hilarious how there's 50 clones of the same thing in the comment section, yall need to go watch Peter Thiels talk at YC from 2011 or whenever. Be contrarian, stop building the obvious thing.

cmsparks 4 days ago | parent

When we started out, people were asking "Why would you want to continue coding on your phone". There's obviously a ton of competition now, but I think it's also validation for us.

Even though this might be "the obvious thing", I think there is a non-obvious way to build it.

CuriouslyC 4 days ago | parent

This project seems like a good idea that didn't have enough of a moat. I'd suggest trying to narrow your target customer from "engineers that want to manage agents on their phone" to "people trying to do some particular kind of task," so you can bake in more value add and automation. You're not going to beat the labs on general tools, but they're not going to be willing to narrow their target customer, so you'll always be able to win at the margins.

cmsparks 4 days ago | parent

Our goal is building infrastructure around the agent tools, which I think is how we'll build up a moat and provide automation value. I agree that competing with the labs on general tools is probably a bad business decision, but I'd argue that just means we should compete on the infrastructure, not the harness/model.

__sy__ 4 days ago | parent

i don't get all the hate in this thread. I literally was about to build this today, using my home server, tailscale, and some kind of web frontend. thanks for saving me time :)

cmsparks 4 days ago | parent

Thanks, we try to make it much easier than self hosting and managing your own tunnels! Let us know how it goes.

koakuma-chan 4 days ago | parent

Correct me if I'm wrong but they seem to proxy all your conversations.

saadn92 4 days ago | parent

Built something like this that’s open source and free: https://github.com/saadnvd1/agent-os

nzxt210 4 days ago | parent

Why don’t use Happy Code? It’s open source and free to use: https://github.com/slopus/happy

cmsparks 4 days ago | parent

We've seen a decent amount of comparisons to Happy, but anecdotally from some Omnara users who have used both, I've heard that reliability and latency when sending messaages is much better in Omnara

We try to provide more features on top as well, including (but not limited to):

* improved web interface

* worktrees

* sandboxing

* richer git management (richer diffs, checkpoints, git operations)

* preview URLs

ex3ndr 4 days ago | parent

Stability was our (Happy) temporary problem, since our DB grown to reach like a TB now, but since we upgraded it is much much better.

kmansm27 4 days ago | parent

Haha yeah, we love happy, seems like you guys are popular in this thread :)

rvz 4 days ago | parent

Good question. Since this is open source why bother with Omnara in the first place? Or perhaps this is a fork of Happy Code and now it is a YC startup.

Just shows that AI has advanced so quickly that it is easy to clone YC startups to zero.

cmsparks 4 days ago | parent

We're not a fork, and from what I've heard from users our architecture is more reliable

sneak 4 days ago | parent

A good reason for not using Happy Code is that they collect your usage data in the iOS app. Not sure what Omnara does, but vibe coded clones don't sell out your data to some random startup wrapping Anthropic tools.

mchusma 4 days ago | parent

getting this error trying to connect github: github_unauthorized: GitHub OAuth error: The redirect_uri MUST match the registered callback URL for this application.

kmansm27 4 days ago | parent

Looking into this, will fix this soon! GitHub auth should be working on the web app, if you try there (assuming you got this error on mobile). You can continue to use Omnara normally without signing into GitHub, you just won't be able to use the cloud syncning feature til you auth with GitHub.

kmansm27 3 days ago | parent

Just fixed this issue! Seemed to occur on web, thanks for reporting this!

tmshapland 4 days ago | parent

Congrats the launch, guys!

kmansm27 4 days ago | parent

Thanks!

itissid 4 days ago | parent

Congrats on the launch. I've been fooling around with using my pipecat MCP(https://github.com/pipecat-ai/pipecat-mcp-server) with WebRTC. The WebRTC is hooked into a Webapp interface and this allows me to "talk" to different containers(projects) on my truenas.

I have just a list of chat sessions on the web app on all my projects. The webapp is modified to launch claude code daemons (borrowed from humanlayer/codelayer) and exposes the outbound STT from the WebRTC into a chat session.

- MCP Auth is via auth0

- Webapp itself is gated by a Bearer token.

This itself gets me pretty far. I am not sure what more this is offering?

My TTS/STT models are local by Kyutai and the voice agent's LLM between STT and TTS is used to determine some basic context: e.g. what project directories, mcp servers to select and what skills to use for launching the daemons.

kmansm27 4 days ago | parent

This sounds solid, similar stuff to what we do! Sounds like this setup gets you most of the way there. We also have a mobile app + notifications. And I haven't tried using a coding voice agent via MCP, I'll try that out soon!

itissid 4 days ago | parent

Good to know its similar. Oh I actually do have a text box as well, but using it to type from the phone is not very convenient. Too much typing, I generally STT into the text box. I don't use it to code much, unless I have specced it out and I know the spec is good. But then to code it up is just a few mins, no?

I spend my time trying to tuning the voice+webapp experience: i.e. how it can explain things, can it surface thinking tokens from claude tools properly etc. The sweat, blood, voice go into `/create_research -> /create_plan` loop before the `/implement_plan`. Sometimes I copy the research and paste it into chatGPT for review or comments as well.

I generally use the MCP to get it to follow commands and explain things to me to make progress in this cycle, and I often pause it and ask for drawing me a mermaid a sequence diagram for events or a block diagram showing how pieces go together.

groovetandon 4 days ago | parent

Been looking for something like this - I feel like I lose a lot of work during lunch runs and on the commute home.

barapa 4 days ago | parent

how is this a company?

fiico 4 days ago | parent

Pretty cool was just thinking about this yesterday if I could Claude code from my phone on the couch on side projects would be awesome

JLO64 4 days ago | parent

I’ve been SSHing into my dev server off of my phone to run Claude Code while commuting, so this is a product that I would love to switch to. I can’t use the Claude iOS app due to the testing set up I have. That said I do have a couple of questions:

- Is it possible to completely disable or not use the remote sandbox features? I would never use them and would prefer my code stays on my device.

- For those of us that are using subscriptions, does it show our remaining usage? I would hate to run out of tokens in the middle of a session.

- One feature of the CC TUI I sorely missed on mobile is the ability to look up and directly reference files via “@“. Is any functionality like this planned?

- (This likely won’t affect my decision to use the service as I’ll just put it on a company card.) $20 per month for a service that runs CC on a remote machine in a convenient matter is steep but doable. Asking that same amount for a running code on my own server seems a bit unjustified, especially since this is pricier than the cost of a Claude pro subscription. Are there any plans to offer a cheaper tier for those of us that just want to run this on our own machines?

kmansm27 4 days ago | parent

Awesome, that's the exact reason we built this!

Is it possible to completely disable or not use the remote sandbox features? I would never use them and would prefer my code stays on my device.

Yes, the remote sandbox feature is disabled by default, and you have to manually enable it for the syncing to start.

For those of us that are using subscriptions, does it show our remaining usage? I would hate to run out of tokens in the middle of a session.

Currently Omnara doesn't show your usage limits, you would have to check that at claude.ai. I'll look into add that though.

One feature of the CC TUI I sorely missed on mobile is the ability to look up and directly reference files via “@“. Is any functionality like this planned?

Yes, this exists in Omnara already!

Are there any plans to offer a cheaper tier for those of us that just want to run this on our own machines?

That's a good idea, we'll think about doing this where we don't offer sandbox + voice, and just have the messaging service.

njarecki 4 days ago | parent

Can you guys please make an iOS app that replicates the Claude code app to hook into this one problem my hat is that it can’t query live DB etc. all the things we need a persistent client based terminal session for. But the app is really slick, so it would be great to have it with the multiple threads sidebar, etc..

kmansm27 4 days ago | parent

You should be able to use Omnara for that use case, unless I'm misunderstanding something

upmind 4 days ago | parent

I met Ishaan a few months ago when he had just gotten into YC, congrats on the launch!! Progress seems great and excited to see what you have in the future!

isehgal 4 days ago | parent

Really appreciate that means a lot. Excited for what’s ahead

ed_mercer 4 days ago | parent

OpenClaw already does all these things and better. It can run 24/7 in one (or more) VMs that I control from my phone, without extra cost.

saberience 4 days ago | parent

I would be blown away if Anthropic, OpenAI, and Google don't all offer this functionality in the near future.

Also, I'm not sure many engineers really WANT to be able to do more "vibe coding" away from their laptop.

Is this really what our job is going to be? Typing in prompts from a mobile phone?

Good luck guys but I think a pivot might be in order.

cadamsdotcom 4 days ago | parent

Great to see. It’ll be great to democratize access to remotely using cli coding agents.

I’ve been iterating the past few months on a solution to use Claude Code on my phone while it runs on my laptop and it’s a lot of moving parts: Tailscale, git worktrees, tmux, an always-on “caffeinate” process, and a ton of hooks & tweaks to fix bugs along the way. It’s become very comfortable but in the process, impossible for anyone but me to understand.

But it’s awesome because I own the machine that runs tests and am not paying monthly for anything but Claude Max - and it keeps going if I lock my phone or go into a cell reception dead zone.

Productising such a thing would be a very interesting challenge indeed.

groask 18 hours ago | parent

Totally relate to the "tons of hooks & tweaks" part. I've been using Claude Code daily to build a macOS app solo, and ended up in the same rabbit hole — hooks, FSEvents, process monitoring, all duct-taped together.

The remote/phone side I haven't solved (your Tailscale+tmux setup sounds solid for that), but the "at my desk" problem — losing track of which terminal is doing what — I ended up productizing into a small menubar app called GroAsk (groask.com). It does two things: ⌥Space to quick-launch any AI, and a dashboard showing real-time status of all Claude Code sessions so you can jump to the right terminal instantly.

Very different scope from Omnara — purely local, purely desktop, no remote/phone stuff. But for the "I have 3 sessions running and forgot which one needs me" problem it's been a huge quality of life improvement for my own workflow.

cadamsdotcom 12 hours ago | parent

Nice. For the “which session needs me” challenge I arrange windows spatially and use numbers for my worktree naming.

So the main repo is always the left-most, then worktree 1, and so on.

Rereading the Claude Code transcript is an excellent tool for getting back into the context of what I’m working on in a particular window.

I struggle to run more than 3 truly complex implementations at once, but can handle as many as 6 or 7 if I’m just fixing little bugs.

fathermarz 4 days ago | parent

What changed from your original launch? I know you were hamstrung by something (updates if I recall).

Was there some unlock that happened to make it viable again?

I was an omnara user until that happened and then I switched to happy.engineering. It’s been okay, but I’m excited that omnara is back

kmansm27 4 days ago | parent

Haha glad to hear that you used Omnara before. In the old version, we were directly parsing the terminal output, which was really hard to maintain. But that meant you could use the Claude Code CLI directly in your terminal, and have the same session appear in your phone.

Now we use the Claude Agent SDK (basically a headless version of Claude Code), and we make our own UI for laptop and mobile. This is way easier to maintain than the previous solution we had. You can import Claude Code CLI sessions into Omnara, but you cant see a 1:1 realtime Claude Code CLI session in Omnara anymore. But we think that a GUI is a better experience than the CLI anyways for managing a bunch of agents.

quxbar 4 days ago | parent

I really miss the old way of doing things. I know it was a maintenance nightmare, but I only really value having an iphone app with native notifications that lets me see exactly the same stuff I would see on my laptop. I don't manage a ton of agents, I typically have one main task I am focusing on and possibly another smaller task on the back burner.

m3sta 4 days ago | parent

Can you make it work in android auto?

kmansm27 4 days ago | parent

We have voice support for this exact reason! Not sure if I'd want to enable people vibe coding from their car dashboard xD

wiseowise 4 days ago | parent

"You're walking in the park when an idea for a new feature hits just..." stop thinking about this shit and focus on the walk in the fucking park. Jesus.

sneak 4 days ago | parent

I already have my OpenClaw instance set up with a user account and associated API key on my Gitea instance, and all I have to do is instruct it in Mattermost and it has PRs up and ready for me, with links. I review them, tell it to merge them, and my CI autodeploys it, all in Mattermost and Safari on my phone.

For sensitive apps, it can't merge them, so I have to hit the button in the Gitea web interface (also on my phone), which does the same thing.

dbbk 4 days ago | parent

How many of these is YC going to fund? Are there no new ideas?

linux_devil 4 days ago | parent

All the best , I always wanted to build something like this for myself.

gregjw 4 days ago | parent

I've got no interest in Claude Code or Codex, I'm an OpenCode user. But this does look neat.

mpaepper 3 days ago | parent

How are the runs isolated? Can I run multiple parallel sessions on the same repo? What about security / sandboxing to avoid exfiltration of data etc? Thanks!

cmsparks 3 days ago | parent

Yeah, we have parallel agent functionality, sort of like conductor. This allows you to create worktrees for your repo and run any number of chats per worktree. On your local machine, we don't have any unique sandboxing capabilities, but we reuse your sandboxing settings from Claude or Codex if you have them set. The cloud sandboxing is more isolated, but still has access to the internet.

nicewood 3 days ago | parent

Cool - I can imagine myself using this. We usually use a local supabase for developing and playwright for UI validation tasks, could your sandbox accomodate this too?

topnde 3 days ago | parent

Congrats on the launch!

I am currently building something similar but only for Codex app (not terminal) https://remotecodex.app An e2e encrypted link between the Codex app and the phone.

jackbuilds 3 days ago | parent

Omnara's approach to running Claude Code and Codex from anywhere could streamline AI agent workflows for SaaS founders. The ability to switch between models based on task complexity is a promising direction for cost optimization.

kundi 3 days ago | parent

If you can improve over existing user experience of other tools, this is certainly worth the price.

How are you handling private data and chats transmitted?

cmsparks 3 days ago | parent

Reposting part of what Ishaan said elsewhere:

> We don't have E2EE yet (it's on the roadmap), so some level of trust in Omnara is required today. All repo operations happen locally on your machine. For messages/chat history: we store those encrypted at rest because we need access to sync across devices, send notifications, and resume agents. Cloud sandboxing is opt-in and would require syncing codebase state.

kundi 1 day ago | parent

Does your service require access to the code? Could you explain what trust specifically is required - is there anything else besides messages / chat history that you store and how long you retain those?

cmsparks 6 hours ago | parent

Sandboxing, which is an optional, opt-in feature, requires persistent access to the code via our github integration + us syncing certain refs to our backend.

However, even if you don't opt into syncing, tool calls will end up sending pieces of code from your codebase to our backend. That's just the nature of how we handle persistence of chats. Though messages/chats are retained until you delete them.

FergusArgyll 3 days ago | parent

This is slightly off topic but...

All demos of coding from your phone or even just agents in general show the user just relaxing in a park or whatever.

If you have tons of free time and you are employed, what do you think will happen? Solve for the equilibrium!

fluidcruft 3 days ago | parent

Just as some feedback, your pricing doesn't make sense to me. I san see having a limited number of sessions as a trial, but for people on $20/mo codex/claude plans 10 sessions is too few and adding $20/mo for omnara doesn't make sense. Yes $20/mo is small compared to Codex Pro/Claude Max plans.

Omnara is easy to get a taste and with that pricing the next step is just going to be: switch to happy. But for people starting out you're just driving people to happy instead and when they upgrade from $20/mo LLM plans you will have pushed them to happy and they'll stick with happy rather than come to omnara.

josefrichter 3 days ago | parent

Very useful for supervising Claude and occasionally steering it. Now that Claude finally auto-suggests next command, it partly offsets one of the biggest obstacles of mobile phones - typing on tiny keyboard is painful.

quotz 17 hours ago | parent

20$ a month seems overly expensive when theres an open source end to end encrypted project called happy coding which does the same. If it was 5$ I would've considered it.