Nick Taylor

Try out one of my favourite features in this new interactive tutorial for Pomerium! 👀

@rishabincloud @OpenAI Have fun!

headed to SF, who is ready to party with @OpenAI 😎

Do I have anyone from @discord in my timeline? Our @openclaw guild is down the whole day and idk what's going on.

In 3 weeks at @devtoolsTO: @tracesdotcom - share agent coding sessions @polarityco - sandboxes for agent testing @super_user_app - agents in your team chat Tidra - AI code maintenance at scale Docsalot - docs agents can read Code Pathfinder - trace vulns across your codebase

Join us today! ⬇️

Now on GitHub, you can just use the rings with whatever pet you like, pass the link to your agent and it should install it fine github.com/petergpt/codex…

@petergyang Curious why you went back. I’ve only been on OpenClaw since late January, but was aiming to try out at least Hermes as well.

I tweeted this as a joke but it's literally what I'm doing right now lol sigh

@siddak_b @petergyang qmd has been working well for me for my claw.

@petergyang At the end of the day you'll realise they all have the same problem: memory

Whether it’s existing consulting firms, new ones that emerge, FDEs from agent vendors, or new internal agent engineering roles, the amount of work that is going to be created to implement agents in enterprises will exceed anything we imagine today. The complexity of implementing agents in any existing organizations is very real. When I talk to large enterprises, as you move from a chat paradigm to agents that participate in meaningful workflows, there are a number of things they need to do. First, you have to get agents to be able to talk to your data securely across your systems. In many cases, enterprises have decades of legacy infrastructure that contain the valuable context for AI agents. That’s going to take a ton of work to go modernize and move to systems that work well with agents. Then, you need to ensure that you’ve implemented agents with the right access controls and entitlements, the right scopes to be safely used, and have ways of monitoring, logging, and securing the work that they do. Next, you need to actually document the processes in the organization in a way that agents can utilize for doing the work. You also need to figure out what the new workflow looks like when agents and people are working together on a process, and who steps in where. Just replicating the old workflow will mute the gains. Oh and you likely need to create evals for your top new end-state processes. Finally, you have to keep up with a rapidly changing set of best practices and architectural shifts happening in the agent space. While it’s fun for people to change their personal productivity tools on a dime, it’s 100X harder to do this in a business process. The speed of change is a blessing and a curse right now for anyone trying to keep a stable system design. All of this means that individuals and companies that develop expertise on the above set of components (and more) are going to be needed to help organizations actually implement agents at scale. This is also the rationale for vertical AI agents right now that can go in deep on a business domain and help bring automation to it. This is a huge opportunity right now whether you’re doing this internally or as an external business provider.

@petergyang I use to use Amphetamine, but now just use caffeinate. 😎 Ships natively in macOS. one-tip-a-week.beehiiv.com/p/one-tip-a-we…

How to keep your agents running even when your macbook lid is closed: 1. Go to Mac App Store and download Amphetamine 2. Go to Settings → Session Defaults → uncheck everything below You're welcome :)

@realsigridjin A&W is 1000% way better than MickeyD’s .

canadian 🇨🇦 folks any thoughts on a&w? their fries just hit totally different and mcdonalds or bk could actually never they use beef with zero hormones or antibiotics it aint a perfect health food but it is easily the most elite fast food choice out there

GitHub if the creators of WinAmp built it. “GitHub, it really whips the llama’s ass!”

@nnennahacks Be careful in the glass elevator! 🤣

I just realized what this gpt 5.5 event feels like. Getting the golden ticket in Willy Wonka. 🎫

@adilmania @sama I'll take an old or new @sama follow lol

i like the new @sama a lot. i feel like i can just ask him to follow me and he'll do it.

So many massive fixes from the team. If you’ve been having issues with your OpenClaw agent the last couple weeks, this is exactly the release for you

We are building the substrate for the next wave.

Seems like forever ago but it was just last week! @AIEMiami 2026 was amazing! 👀🌴

If you’re having trouble with OpenClaw v. 2026.4.29, run “openclaw update —channel dev”. Gets you the latest incremental merges ahead of the public release. Much, much better now.

any word that starts with sh or ch..Autumn says "shit." Like her putting on her shoes..she keeps saying "shiiiiiiiiit"..or I'm like okay daddy is going to go to church..she's like "daddy shiiiiiiit" I'm like omg stop 😭😂😂😂😂

@rachelnabors First one

Pick one

Launch Your First Firecracker microVM 🛠️ If you keep running into Firecracker (in the agent sandboxing context or not), and wonder what these microVMs are and how easy or hard it is to start one "from scratch", I've got a step-by-step guide for you 😉 Based on 3 years of experience using Firecracker to power iximiuz Labs playgrounds: labs.iximiuz.com/courses/firecr…