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.
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.
An example of a non-coding "asynchronous agent" in my mind is something like deep research. It runs for a while in ChatGPT or Gemini, and when it's done, it produces a markdown file or google doc with its findings. The parallel with your definition of "asynchronous coding agent" is that I'm not watching it work or involved in the process.
But your last point highlights exactly why the sync/async distinction doesn't hold up as a binary classification. Even with deep research, I go back and forth on a plan synchronously before sending it off to run async. Any good asynchronous coding agent should work the same way.
So fairly large players are using “async agent” to mean something specific, which seems enough to warrant defining it. It also makes sense that it’s far less common than “autonomous agent”, since “async” is mostly used by technical folks, which is a much smaller audience. I’m definitely in that sf/swe/tech/startup information bubble, but that's where this stuff is taking off.
If you're talking about the async agent described in the post (already regretting calling it that, let's call it orchestrator agent instead), looks like https://code.claude.com/docs/en/agent-teams is trying to achieve that
Hey, thanks for trying to get it working, this is unexpected! The reason we have the localhost in the callback is so that we can write the api key to ~/.omnara/credentials.json, so for future use, you would just use that api key. We temporarily spin up an endpoint on your computer during auth time so that we can send a request to it with the api key.
The workaround is to just login to omnara.com, click on your email at the bottom left, click on "API Keys", and then create an API Key named CLI Key.
Then copy that key, and make a file at ~/.omnara/credentials.json, and the contents should be:
{
"write_key": "<YOUR-API-KEY>"
}
Then you can run omnara, and it shouldn't ask you for authentication again. Let me know if this works out!
Here's our privacy policy - https://omnara.com/privacy.
The main information we store is everything you see in the Omnara dashboard/mobile app. e.g. agent conversations are stored in our server so that it can be synced across mobile and web. If you choose to delete the chat, we immediately and permanently delete those messages from our servers. Our backend is completely open source, so you can see exactly what information is being stored in our db.
the missing session id might occur if you're not using a recent version of claude code! can you try updating your version of claude code and running "omnara" again?
Email ishaan@omnara.com with your google play store email account. He can invite you to being a tester for the android app while it's making its way through the review process!
We've noticed that using terminal emulators (e.g. warp, alacritty) lead to issues with pasting things into Omnara, do you happen to be using a terminal emulator? If so we can look into it. But with the native terminal, pasting should work in both the terminal and the web/mobile apps
Technically, all the messages are stored in our DB (anything that's visible in our dashboard is stored in our DB), so if we wanted to, we could see the messages flowing through Omnara. If you delete a chat instance, the messages are deleted immediately, no soft deleting.
But yes this is a good point, it's a big reason we open sourced our backend. We've thought about doing client side encryption before sending messages to our servers, but that probably won't be implemented in the near-term.
Looks like someone in our github reported that the termios library we use isn't compatible with windows (https://github.com/omnara-ai/omnara/issues/72), so might take a bit longer to find a workaround for this
This is cool! We've had a bunch of people request for voice control, they've used the native keyboard voice control for now, but it's not great at getting contextual recognition of words (especially technical things). It's on the roadmap, so I'll reach out when we get that started!
Thanks! We're going to make the mobile app and frontend open source too, I just haven't had the time to do it properly yet. Maybe I can email you the source code - if you're interested you can email me at kartik@omnara.com. Otherwise, we'll open source the mobile/frontend in the coming weeks and you can check it out there.
Thanks! There's nothing inherently macos-specific about this, I just need to get my hands on a Windows machine to test it out in case there's some path issues. I'll try to do that soon and update you
Really cool, I actually haven't met many people using cursor background agents. I do think Anthropic is working on a web app for Claude Code (saw it in some thread somewhere), so I'm sure they're also working on a mobile app. In that case, the value for Omnara + Claude Code diminishes, but we're able to support any agent, so if every company has their own app, but a user can use all the same agents from a single platform, hopefully they'll choose the single platform.
Oh interesting, we've gotten some requests for supporting opencode as well. Opencode would much easier to work with than Claude Code since the backend and frontend are separate and open source. Maybe we can beat them to the mobile support :)
I still think that human taste is important even if agents become really good at implementing everything and everyone's just an idea guy. Counter argument: if agents do become really good at implementation, then I'm not sure if even human taste would matter if agents could brute force every possibility and launch it into the market.
Maybe I'll just call it a day and chill with the fam
I'd say it's more flexible! At least we're trying to head in that direction, since the SDK allows you to hook up any agent to our platform, not just CLI agents. And eventually we want people to be able to add their own frontend components for their agents, which would make the experience more custom than a terminal UI. Although yes, if you just want a 1:1 CLI agent on your phone, then mobile SSH clients might make more sense.
Yeah, I would say that most Claude Code users are pretty technical, but I was surprised to see that there's a decent number of non-technical users using Claude Code to completely vibe code applications for their personal use. Those users seem to love tools like Codex (the openai cloud UI one, not the CLI) and things like Omnara, where there's no setup
Exactly! My ideal vision for the future is that agents will be doing all grunt work/implementation, and we'll just be guiding them.
Can't wait til I'm coding on the beach (by managing a team of agents that notify me when they need me), but it might take a few more model releases before we get there lol
You're correct, that's one pro for vibetunnel/mobile SSH clients - they're a direct connection to your machine. For our platform, the messages flow through our server, which enables some use cases like push notifications and easier setup/reliability, but for a tradeoff of the data not being local.