Been integrated a codex remote feature to my NovaScale app (with in-app tailnet connectivity) using remote app server too, it works well for me, though the websocket is experimental, but seems it keep schema compatible well.

This is the motivation I built the app NovaScale with in app tailnet connectivity

I was thinking the herdr remote features is nice to have in my app, given this herdr multi machine support, perhaps I need to reconsider how I integrate it in the future

Have a macmini m4 32G, not the pro version, previously everytime I tried local LLM is a bit disappointing, and I finally decide to not waste time and perhaps in the future invest a better hardware to server more modern and dense model

I am curious is what is the 80% request served by this setup, I was using it for OpenClaw which run serveral cron jobs that discover stuffs over the wide internet, check my support system's unanswered tickets, browser X and some social media for me to filter the valued ones(though I have to say even with GPT 5.6 sol, the quality is low for the timeline X sent to me)

Btw, Tailscale is quite cool and did a good job, I was using it to serve the local LLM and connct the openclaw on a Linux Machine to it.

You have tried Qwen 3.8 27B before coming to this conclusion, I hope? It's an incremental improvement over 3.6, but I mostly want to make sure you didn't just try running some old junker before coming to this conclusion.

As a engineering all my career life focused on networking, I am so depressed that IPv6 still not fully replaced IPv4

We have dozen of RFCs and vendors gears support IPv6 as well, but it just not finished

It's fine. IPv4 addresses might get too expensive at some point, encouraging their deprecation. Or it's entirely possible having the option of IPv6 prevents IPv4 addresses from getting prohibitvely costly. Either way, IPv6 has its role.

being built a iroh based distributed notes app for myself use

and see tailcat come out, trying to replace iroh with this to do some experiment because i really love how tailscale works and invest much time to the stack

True appriciated of open source this, combine the tailscale open source client core with this, i think it can unlock more stuffs

Thanks for sharing

Being dad is really hard joyful, you watch they grow from a tiny one to some big one which argue with you also sometimes care you when you sad

I quit from a high pay job because I want to enjoy more time with kids because I feel not get enough in my childhood

I like to read philosophy and settled with existentialism, this helps with the stress of low earning compared the previous time

Life may all about trade off, we may not lucky to get everything we want

So this is basically a wrapper over the existing agents from differnt vendors?

Just poke it a bit and find for codex it use app server protocol too

> Not backed by Y Combinator

This is humor, isn't it?

yeah it's basically an alternative GUI for Codex CLI and other clis, I built this because I got frustrated with those Electron Apps performance

Which electron apps?

the official ChatGPT and Claude app

Thanks for the frankly sharing of the journey, being in the same boat, after two years of not-worth-to-mention revenue from appstore, it seems start to get on track a bit now

I think I am not the lucky one to get overnight success and like in the post get the lucky time on iOS 15 release

Being writing a long article to record my indie app developper journey, Hope I can read in calm of it one decade later

Given my codex have limited usage and I get a idea to build a on device clipboard translator with menubar when read a article find some words not seens before

So i launched agy and find seems it have a 3.7 flash i thought its latest,until i see this article i know it's just released

after serveral rounds prompt(the initial prd prompt is by chatgpt), it use 2.9k user message token and 42.5k reponse tokens with gemini 3.7 flash(low) after i check the status, i got a working on device translator, its cool

the model seems also p and retty fast and the generated app looks good and easy to use

but agy cli is a bit unintuitve and i also check the guy that release the latest agy, seems the guy does not commit much ? or perhaps agy does not open source and only use github as a issue feedback channel

I only touch some emacs lisp and never do Common Lisp But seems years of coding experience make me think those tenets in the article reasonable There are indeed elite programmers as I see in my career it’s rare also we do not need to be sad Maybe it’s time to learn some Common Lisp given it’s a good day for exploration and prototyping