Building for agents. https://xitter.cf/t.co/Nabcx4aCiE gives your agents a portable file system. https://xitter.cf/t.co/LSC8fREKQN lets them build apps and experiences with simple markdown.
Joined April 2025
- Tweets340
- Following87
- Followers336
- Likes83
Pinned Tweet
I’ve been thinking about why AgentsFS feels powerful.
For models, test-time compute means the model spends more tokens thinking during the response.
For agents, the equivalent isn’t just “think longer when asked.” Instead, it’s doing useful cognitive work between requests: summarizing what happened, compressing raw material, resolving contradictions, writing durable briefs, cleaning up stale notes, and leaving the next agent a better starting point.
That changes the shape of “memory.”
A lot of agent memory today is either hidden memory in the agent harness, raw chat history, or bigger context windows. Useful, but incomplete.
Agents don’t just need more context. They need better future context.
Frontier models get better by spending more tokens reasoning at inference time.
Agents get better by spending more time improving the environment they’ll infer from next time.
That means turning messy inputs like docs, transcripts, or failed attempts into concise, accurate, source-cited, up-to-date notes the next agent can actually use.
agentsfs.ai is just a very simple to understand, completely local, lightweight implementation of a filesystem where agent knowledge can compound.
Been using Muse for the last few days. Truly great. Only thing is, I find myself being super careful with what I share. Compared to my OpenClaw for some reason I have a mental block with giving Meta access to my Gmail.
It’s great but hard to get over the negative mark from the bad rep Meta has built over the years.
Also interesting to see how much the @verge’s coverage was almost entirely about how Meta is spying on us over the last few days…
I get the hype about Jev and the tech is real. But one thing I’m personally missing is a measure of how accurate it actually is.
Surely there must be tons of classification and ranking evals we can apply Jev against to get some baseline of how good it actually is at decision making.
Just published a self-service site that lets you configure your own cloud Omarchy instance for free (just have to pay AWS for compute): xitter.cf/seekinggradient/status…
Okay, here's what I've been working on: Cloud Window 🙂 getcloudwindow.com
After the last demo, a bunch of you asked how to try it. I've been making the setup easier, and the first DIY release is now available.
An Omarchy desktop in your own AWS account, streamed to your iPad, phone, or laptop. Same files, same apps, same session.
I really love using this on the iPad. Here's a look at the experience, with the setup walkthrough below.
I got Omarchy running on my iPad, Pixel, and M4 Max MacBook Pro 🤯
It can basically run anywhere and is super responsive. The trick was that I set up a VM on AWS and can attach to the same computer on any device through Moonlight + Tailscale. Same files, same apps, same session.
I built software around it to adapt the desktop to different screen sizes, get keyboard shortcuts and inputs working correctly, and automate the AWS setup. Plus a web dashboard for starting, stopping, pairing devices, and tracking estimated costs.
Really love this idea: your device becomes a window into a computer you can take anywhere.
Still experimenting, but it’s working. DM or reply to this thread if you’re interested in trying it!
Thanks @dhh for creating this exciting OS.
Okay, here's what I've been working on: Cloud Window 🙂 getcloudwindow.com
After the last demo, a bunch of you asked how to try it. I've been making the setup easier, and the first DIY release is now available.
An Omarchy desktop in your own AWS account, streamed to your iPad, phone, or laptop. Same files, same apps, same session.
I really love using this on the iPad. Here's a look at the experience, with the setup walkthrough below.
And here's how to set it up.
This first release is for people comfortable using their own AWS account. The video walks through the prerequisites, deployment, and connecting your devices.
Cloud Window's DIY setup is free; you pay AWS for the infrastructure you use.
Still early, so I'd really appreciate feedback from anyone who tries it. Let me know where you get stuck!
getcloudwindow.com
I've been working for the last several days to make it really easy for people to spin up their Omarchy cloud instances - stay tuned for the full result tomorrow. Sending this to you from the new, streamlined Omarchy setup on my iPad.
Man, using my Mac after being on my PC hardware for the last few days...My Mac's screen is so big, so nice, and the keyboard and trackpad are incredible.
Seeking Gradient retweeted
I'd always thought AI was terrible at design, but after reading today's 🤯 post by @anshuc, I realized I was just doing it wrong.
"AI models are capable of amazing creativity, but that creativity gets stifled. LLMs are trained to be next-token predictors: they look at a sequence of text and predict what typically comes next. Great design is exactly the opposite of this. Great design bends the rules and delights users with memorable, unexpected choices."
@anshuc led design and engineering teams at Apple for 12 years. In his words: "Most people only see 1% of AI's creative potential. I want to show you how to tap into the other 99%."
His 8 techniques for breaking out of the 1%:
1. Use seed strings to inject variety
2. Be much more ambitious with your prompts
3. Create positive feedback loops with subagents
4. Use image generation to enrich designs
5. Use video generation
6. Cut out elements that don’t add value
7. Remove AI tells
8. Rewrite copy by hand
Read the post here: lennysnewsletter.com/p/how-t…
P.S. This design was made by AI 👇
Coolest thing I did today on Omarchy is to add a "fire and forget" keybinding for your favorite agent. Just press Super + A and dispatch a task to your agent. Press Super + Alt + A to see all your previously dispatched tasks
Couple things about getting Omarchi running:
1. Codex set this whole thing up by controlling my new Windows machine from my Mac, including making backups in case anything went wrong.
2. Windows/Microsoft is slimy. They forced me to sign in to Microsoft, and issued takeout requests to my Gmail. Also, sent me a bunch of spam about discounts and cash back.