This is really cool! I made a post months ago doing the same thing with my Android phone using ADB. However, I haven’t thought about how to do it with an iPhone since my personal phone is an Android. But RCPair sounds like a legitimate solution, so I’ll check it out.
https://t.co/hJcmJ2vzRp
I've been using a Linux PC at home as my remote dev machine for the past few months, with my MacBook Air as a lightweight client. I've really enjoyed being able to delegate work and close my laptop while it keeps running.
But some workflows still brought work back to the Air, especially iOS simulator testing and Codex computer use on macOS. So I added a used MacBook Pro as another remote node.
I wrote about the setup and included a demo of the agent testing my app on web and iOS, then sending me a recording:
https://t.co/rDh7Q87d9A
@jullerino How you handle Computer use on the mac from a Linux thread ?
I have a similar setup and I am trying to use Codex CLI to delegate computer use requests to the mac
@freddier At DealMaker, we use https://t.co/Q3F4ySK48F for meeting recordings, and it adds that to the Calendar, but it uses the same hourly rate for all attendees
A recent video from @theo about his Linux dev fleet resonated with an experiment I’d already started: moving my coding agents and dev environment off my MacBook and onto Linux.
I turned an old gaming PC into a Linux dev box. Then came the real wow moment, from a restaurant, with my MacBook off, I requested an app change through my Android phone.
The agent worked on Ubuntu at home, and I tested the result on the same phone.
This video shows that loop: Tailscale + wireless ADB + Metro + Codex.
Full story:
https://t.co/hJcmJ2vzRp
Tiene sentido y parece una buena idea, pero no sé si opino lo mismo con los proyectos creados con IA.
https://t.co/yIYnGc6aMI
Creo que sí tiene sentido desde el punto de vista de costos de CI e infra, pero el explicitamente decir que no se puede hostear un proyecto "Projects written and maintained with heavy use of LLMs“ creo que no es muy coherente con cómo el desarrollo de software está evolucionando.
I’m using a similar workflow, but not with a VPS. I have a headless home desktop running Linux with Tailscale, and all my development servers, code, and agents are hosted there. I use the Codex app’s remote client to manage the agents, and when I really need to see the code or check localhost, I use VS Code with SSH tunneling.
Being able to close my laptop without stopping the development server or the agent is a huge advantage. I don’t see the point of having a MacBook Pro to run everything; now, my MacBook Air is perfect for my needs.
I’ve been experimenting with personal agents like Hermes, and it made me wonder how many AI products are really skills wrapped inside standalone apps.
I built an AI nutrition tracker to understand meals from text or photos, estimate calories and macros, and save everything to a Google Sheet I control.
To make it reusable, I originally built a Python backend, web app, Telegram bot, OAuth flow, database, and user system.
Eight months later, I recreated its core workflow as a plain-text skill in around 15 minutes and two prompts.
This connected with two ideas I had recently encountered:
@theo arguing that capable models and tools can reduce some products to structured instructions:
https://t.co/GMZ6uBiIbQ
And Julien Avezou writing about building for agents, not just humans:
https://t.co/5qZhYBzzlv
That experiment made me question how many other AI products could be compressed into simple agent instruction.
Today, I would start with the skill and only build the standalone product when the workflow proves it needs one.
https://t.co/EXcvVL8wWp
React Native on iOS doesn't support ReadableStream. When users switch apps mid-response, the AI keeps generating to nothing. This dev solved it by making the server keep going after disconnect and persist the full response to the DB.
{ author: @juandastic }
https://t.co/9cihw8KJDS
12 years building web apps. Zero mobile experience. Last month I needed an iOS app for my side project so I just built one. Took 3 days.
The real unlock was not React Native or Expo. It was having AI in the workflow. It did not write the app for me but it removed the friction of learning a new platform. I moved at the same speed I move on the web.
Then iOS broke everything. Turns out when your user switches to WhatsApp mid-response, iOS kills your network request. The AI keeps generating server-side, burning tokens, but the response never arrives.
Had to rethink the whole streaming architecture to handle disconnects gracefully.
Full writeup: https://t.co/vBDGQgV2wB
@deshrajdry Great article, this reminds me of the article made by @BennettSchwartz with similar ideas of why markdown is not a memory
https://t.co/hV7yvZMH7t