Hacker News Reader

Comment by throwatdem12311 | Hacker News Reader

> development environment

First screenshot is of a phone.

Yeah I’m never installing a coding agent on my phone.

You can also use it as a plain old chat client. I prefer it over OpenWebui because I can actually carry over my OpenCode configuration, which has specialized subagent definitions (for example, the "research" agent fires off a bunch of "web search" agents that use a cheap model to fetch and summarize, and the more capable "research" agent pulls it all together, decides if more search effort is necessary, etc.). So I can VPN into my home network and boom, self-hosted chat interface that's more capable than what you can (easily) do in OpenWebui.

I frequently use openchamber on the go. It's very good at this.

Why not?

Both codex and Claude have remote from phone. I’m personally using cli + terminal from phone.

I’m sure I’m not the only one.

Are there any Android remote terminal apps that don't suck on mobile? Termius is painful.

I’m using Termius.

It’s not great but it’s better than anything else I’ve tried.

It doesn't work with tailscale. Won't prompt you to go through the web sign in.

if you're using herdr, i built a plugin exactly for this reason. its a pwa so requires a proper frontdoor for secured access (tailscale, netbird etc.).

https://github.com/AltanS/collie

Using it now. It seems like I finally found something that works. Having the same agents accessible on the laptop in a large TUI and quickly viewable from my phone has been useful.

Tailscale integration works well too. The mobile notification setup was a little clunky and the instructions were confusing, until I found the directory with the shell scripts. It should probably expose a herdr action to generate the keys and include that in the documentation.

One thing though: the subagent lines should be clickable like they are in Termux but your actions box absorbs the click and focuses the GUI input line.

I only saw this now, thanks for writing this up. Will take a look and address these in one of the upcoming releases.

Tiny screen that can barely show any information and the awkward miniature keyboard that's slow to use and gives no feedback, it's a pretty awful way to do anything.

lately, i like to try to spend the morning talking through and framing up a few very detailed initiatives for parallel efforts that each spawn and orchestrate their own tasks, then feed them to /goals and go for a nice walk in the park, get some groceries, check in on the orchestrators and spawned tasks along the way, steer them from the phone.

so far it's been working pretty well for me in most cases, but not always. having a few parallel efforts in motion means that even if one goes off the rails, i can pause it and still make progress on the others, then fix it up when i get home.

no issues here with a small iPhone and Blink. I can change the text size on the fly, and am very used to typing on the phone keyboard. Also use dictation

Because I’m not putting work in my pocket.

id rather have it in my pocket and get stuff done while im out doing what I feel like doing instead of sitting in an office all day.

And I don’t want work bleeding into every aspect of my life. When I’m out doing something I’m not working. When I’m working, I’m working - and it stays in the place that I work.

Bring tethered to work 24/7 isn’t freedom from work, it’s enslavement to it.

I don't use it for work I use it for my private projects and this allows me to work on them even when I'm commuting which used ti be wasted time.

Reply on news.ycombinator.com