Inspired by @theo Cli Proxy API Quota Manager. Will share in 30 min! :p
Here it is: github.com/nikuscs/cliproxy-…
Imagine having the whole community to love something, but you still insist in doing something else. Major lose.
We've decided to sunset Arc on December 22, 2026.
That's not an easy sentence to write. We spent years building Arc and celebrating each and every release along the way: we have so much pride and love for what we made alongside the Arc community.
Our priority is to deliver best-in-class security for our members. Keeping a browser secure takes constant, dedicated work that is only increasing in the age of AI. Dia was built from the ground up to meet today’s security standards, so that's where our engineering and security teams will focus moving forward.
We've worked to make switching to @diabrowser as easy as possible for Arc members. Here's how:
· Your passwords, bookmarks, extensions and history come over to Dia seamlessly.
· Spaces, Folders, and Tab Groups are in Dia and import over with your data intact.
· Dia now surpasses Arc benchmarks in stability, speed, and security.
· The browser features you use in Arc are free in Dia, and the AI is optional.
Thank you for using Arc, for pushing us to make it better, and for building alongside us. The team that made Arc is the same team behind Dia, and some of our most ambitious work is just ahead. We'd love for you to be there with us when it lands.
Its 2026, AGI approaching, and we still cant re-order what Gmail account or google account should be the first one without logging out every single account.
Sharing for reach, to all PHP folks, ensure your up to date by tomorow.
Continuing my bots clone experiments 🧪 this time using @pidotdev durable + a mobile client. Crazy how good the DX is for PI durable. Mobile App is using Expo and frontend Tanstack Start. Iv extracted a small daemon that holds pi durable then you can pair it to any "client" of your choice.
Trying to downgrade my GPT Subscription but unable to do so because i'm a delinquent 😂, maybe its because i have a open invoice still to be paid, but in any case funny the message that it shows on the Rest endpoint. The UI shows
"We couldn't confirm this plan change. It may still be processing. Review your subscription in Billing before trying again."
Is it me or Astra & Sol models are unusable at this point? i dont remember being this so damn slow 🫠 at this point no matter how many resets @thsottiaux gives out. Even at Medium effort it takes sooo much time to do a simple file edit. Claude smokes it out by a good margin. Sol 6 was peak model for OpenAi.
I love @bot but i'm not sure i like how it handles memory / instructions, it works pretty good most of the times, but personally i like deterministic rules & not being vendor locked-in. Wondering how everyone is managing their bots to ensure it doesnt drift away from what you want.
- Keep bots memory really small and force them to read instructions more like Hermes, Openclaw.
- Ensure to have a "Soul" bot that clears up contradictions on your memory and enforces to write your rules on the actual file instead of being "lost" in the memory itself.
Probably a spicy 🌶️ take, but i never liked memory for any kind of AI stuff, memory for deterministic agents should have been rules/skills at first place, i know there is a few edge cases were memory is useful but most of the time for me its not really good. Every now "world" should know exacty what your rules are, until we make this somehow perfect, memory wont save it either.
Ok so the first version of Orbs was running on multi-harness but i was wondering why not using @NousResearch Hermes agent since it contains mostly everything out of the box? All you need is a little nice UI on top of Hermes :p
With Hermes a few features we get for free:
- Models fallback, Memory, Workspaces, Permissions, Approvals, Routines, Any provider that Hermes supports
- From the Original Orbs iv also added: Artifacts with persisted state, Notifications, Desktop App, Themes, Agents.md and Skills Overrides, Global Search
Im not sure if ill share this one, since my goal is to actually put my own taste on it , keeping it simple, i see a lot of bots stuffing features all over the place, simple is better!
btw if you want the original repo : github.com/nikuscs/orbs someone add @pidotdev durable and ill consider switching back 💀
loool pretty wild, i like to live in danger, so ill stay on 27.1 😆 We are so back! 2026 is turning out to be one the most exciting years for me since i learned how to code. Everything is possible!
Been using Tanstack Start for mostly 2 years now, really recommended! All my "serious" projects run on start. Never found anything that it couldnt do!
TanStack Start 1.0 is officially stable! 🎉
A full-stack web framework for React and Solid, already used to build millions of apps, from Fortune 500 companies to your favorite tools and weekend projects.
tanstack.com/start
As promised here is the Github Repo: github.com/nikuscs/orbs
Stack: Tanstack Start + ORPC + Bun & optional Cloudflare DO.
If anyone wants to help:
- Direct Messages from bot to bot
- Routines
- PC Spanshots for previews
- Implement other harnesses ( currently ships with PI )
Or just clone it and make it yours! :p
Having some fun doing my own Grok Bot @bot ( Dots, Muse ) alternative with @tan_stack start, @pidotdev + @Cloudflare durable objects! 💅
- Multi-harness Support
- Multi Decision Room Routing ( Jev, LLM Judge, Roundtable )
- Memory for Bots, Rooms & Global
- Reactions 👍
- Daemon runs locally + web on cloudflare
- File Support with R2, Room data & Bot Data exportable on CF durable.
Will open-source next week hopefully, so give a follow & stay tunned.
I was going to use some open-source alternatives or fork them, but most of them are damn sloppy, my ideia is to use this for myself since OpenClaw & Hermes lack group collaboration & a proper mobile / responsive design. Dots is not available in EU, Grok is "locked" to grok models but for me its still the best in terms of UX/UI overall so congrats to Cursor & Xai Team :p
Having some fun doing my own Grok Bot @bot ( Dots, Muse ) alternative with @tan_stack start, @pidotdev + @Cloudflare durable objects! 💅
- Multi-harness Support
- Multi Decision Room Routing ( Jev, LLM Judge, Roundtable )
- Memory for Bots, Rooms & Global
- Reactions 👍
- Daemon runs locally + web on cloudflare
- File Support with R2, Room data & Bot Data exportable on CF durable.
Will open-source next week hopefully, so give a follow & stay tunned.
I was going to use some open-source alternatives or fork them, but most of them are damn sloppy, my ideia is to use this for myself since OpenClaw & Hermes lack group collaboration & a proper mobile / responsive design. Dots is not available in EU, Grok is "locked" to grok models but for me its still the best in terms of UX/UI overall so congrats to Cursor & Xai Team :p
As promised here is the Github URL: github.com/nikuscs/orbs
Enjoy!
Funny enough a lot of people are missing the point of this post, he prompted his way to refactor Campfire into 3 languages, AI got slopy implementations in Exilir and Go, while rust own by a good margin, point being, AI is well trained on rust, its not a framework fight, its a test on how good AI understands a specific language. For instance Vue/Solid is a nicer langue but React wins every single day.
I've had agents implement and optimize the Campfire web app in Elixir, Go, and Rust. Yes, Ruby is the slowest. I didn't care about that when the pay-off was huge in terms of productivity and developer joy. But if you're no longer reading the code? github.com/basecamp/once-cam…
Readers added context they thought people might want to know
The shown benchmarks use non-equivalent implementations: Elixir routes all DB queries through a single GenServer with Redis for jobs (retained from Rails), while Rust uses in-process queues, omits CSRF tags/fields, and applies other caching changes.
github.com/basecamp/once-…
raw.githubusercontent.com/basecamp/once-…
github.com/basecamp/once-…
github.com/basecamp/once-…
x.com/zachsdaniel1/s…










