Get the top HN stories in your inbox every day.
itissid
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
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
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.
jpallen
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
Thank you! Yeah, a big selling point of Omnara is that it "just works." Let me know how it goes!
jpallen
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
> 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
lalo2302
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.
GraffitiTim
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."
ywvcbk
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.
saberience
You couldn't vibe-code Dropbox in an hour though...
actionfromafar
You wouldn’t vibe-code a car...
gregjw
hmm, i wonder how long it would take nowadays actually
tomasphan
Dropbox is not a tool solely for developers though.
blahblahson
Drop Box is free though.
gverrilla
I migrated away from dropbox to seafile. 2gb free plan to now unlimited =) total: 3 hours with claude code.
cmsparks
they're free up to a limit, just like us!
koakuma-chan
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
Yeah, it's only at a 6.355B market cap, complete failure!
redrove
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
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
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!
busch_j
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.
ciaranmca
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
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.
petervandijck
HN never disappoints!
ncphillips
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
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
I can't sit back down at my computer and cd/ssh/tmux into that same environment.
RobMurray
How does this compare to Happy Coder? https://github.com/slopus/happy
cmsparks
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
splintercell
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.
whazor
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.
sanufar
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
Also your promo video is really fun! https://www.omnara.com/assets/landing/video/movie.mp4
kmansm27
Haha thanks! It was fun to shoot :)
jdmoreira
If you can see the messages unfortunately thats a deal breaker for me. If its encrypted end-to-end than I’m in.
isehgal
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
sneak
> 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".
kmansm27
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!
unsupp0rted
Hysterical E2EE
kovek
https://happy.engineering/ says that they have E2E encryption. Is that true?
kmansm27
Yes, they have E2EE, but it comes with some limitations in the features they're able to provide.
CuriouslyC
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
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.
renato_shira
[flagged]
kgc
I think the native Claude and Codex apps already do this for free. They even have the voice input.
kmansm27
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
> 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
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
elxr
> 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.
perfectus
I think you could give it a try at vibedoctor.dev. They probably use Sandbox and they charge only the Sandbox price. I think it's better if you don't want to keep your local system tethered online and also you can use Claude or Codex subscription.
JLO64
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
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.
zomglings
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
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.
Get the top HN stories in your inbox every day.
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
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!