Founder and Editor-in-Chief @MacStoriesNet. Writer, podcaster, and builder. I write about Apple and AI. Get more MacStories: macstories.net/club/
Rome, Italy
- Tweets 114,172
- Following 1,300
- Followers 85,073
- Likes 19,494
Pinned Tweet
I reviewed the M5 Ultra Mac Studio with 256 GB of RAM.
It’s the dream Mac for local AI agents. And I’ve gone local-only with Hermes.
My story, with LOTS of interactive charts:
macstories.net/stories/m5-ul…
102
113
1,734
479,573
LOTS of updates to my Apple Reminders CLI, RemCTL, over the past few days:
github.com/viticci/remctl/re…
Thanks everyone for the suggestions and PRs, keep 'em coming 💪
I built Apple Reminders…inside ChatGPT.
This is real, and it's a native ChatGPT Extension you can try right now. Free and open source.
Version 2.0 of my Reminders CLI, RemCTL, is out now with complete support for MCP and the brand new @OpenAIDevs MCP Extensions.
With RemCTL 2.0, you have a power-user interface for Reminders inside ChatGPT for Mac. You can use keyboard shortcuts, there's a ⌘K palette, and view tasks as lists, Kanban, or Calendar. It's basically "Reminders Pro".
But most importantly, you can work with ChatGPT in this Reminders UI and ask it to do whatever you want. Attach any task to a conversation, or select multiple ones and pass them to ChatGPT. I was inspired by @danshipper's concept of "Codex apps", and when I saw @mxstbr's announcement yesterday, I knew what to do.
This feels like a brand new way of getting work done, and I'm excited to build more.
Have fun!
github.com/viticci/remctl
3
1
20
2,105
RT @_inside: Of course the first thing I did with my iPhone 18 Pro was to write an app that allows me to control the variable aperture from…
23
102
Okay so this is pretty wild, here's what I've done:
Set up a Cua Space on the M3 Ultra Mac Studio with 512 GB of RAM, with @t3dotcodes running on the M5 Ultra with 256 GB.
Claude in T3 Code can now orchestrate computer use on another Mac on my Tailnet. There are currently 8 Xcode simulators running on the second Mac, so I can free up RAM for local AI on the M5 Ultra. It rocks.
The @trycua team keeps impressing me.
1/ We're reimagining what it means for your agents to work with all your computers.
Today we're excited to share Cua Spaces, built on Cua Driver and our virtualization stack, rolling out on macOS today.
Download it now, it's free and source-available: spaces.cua.ai
9
7
180
19,140
This was almost way too easy, @natfriedman @alexandr_wang 😮
I turned my Xteink eReader into an always-on Muse pocket display for Calliope (my Muse) to display itself and show status updates.
And this attaches with MagSafe to my phone, so I can always see relevant updates from Muse by just turning my phone around.
The setup flow in the Muse app was super smooth and you can just ask Muse to load or automate content on the display.
I genuinely love the hacker-friendly aspect of this. Well done.
59
47
920
136,933
If you want to play around with this:
The device (affiliate link): amzn.to/4zcc2KG
Open sourced the companion software: github.com/viticci/muse-pock…
Have fun!
6
1
80
8,380
This is concerning:
macstories.net/linked/apple-…
75
20
592
311,967
Federico Viticci retweeted
Today for Club members, I wrote about how agents using the Spark Mail CLI have changed the way I manage email. macstories.net/club/macstori…
1
2
1,683
Federico Viticci retweeted
🚨 Club MacStories member who listen to MacStories Unwind+:
You must log into your Club account on macstories.net and resubscribe.
Sorry, but it's a one-time requirement.
RSS Feed: macstories.net/my-feeds/
More details: macstories.net/club/macstori…
2
2
2,035
Federico Viticci retweeted
Since my return home from OpenAI's DevDay, I've been working with my Dot all day long.
Here's what I like and what needs work on @macstoriesnet: macstories.net/stories/opena…
1
8
2,198
ok this is extremely cool and I already have an idea for an e-ink device I have 👀
"It’s built by hackers, for hackers, just for fun."
🚨 side project alert 🚨
Announcing Muse Gadgets, an open source ESP32 firmware and Linux sdk so that you can make hardware devices that work with Muse.
Grab an API token from gadgets.muse.ai and point your favorite coding agent at the github repo to build your own peripherals for Muse.
1
42
9,093
What works well and what's broken in Dots.
This is a great overview by @johnvoorhees and I hope OpenAI considers this feedback.
Lots of potential in Dots, but seems quite rough and too basic right now.
macstories.net/stories/opena…
1
45
7,733
One of the parts of @bot that really works for me is the multitasking aspect of it all.
My primary bot can spin up group threads with other specialized bots (coder, researcher, etc.), which can then spin up @cursor_ai cloud agents, and coordinate. Today, I deployed new features for one of our internal @macstoriesnet apps by doing voice mode with primary bot, which then orchestrated the rest. (Including a @NotionHQ board to keep track of everything across bots.)
From a product perspective, none of the other hosted/cloud assistants (Muse, Dots, etc.) currently match this.
Will be interesting to see if others follow this approach (and I think they should).
16
4
175
23,818
As always, lots of indie apps covered in this one!
We're trying our best to work through our backlog 😅
(And if I still haven't responded to you, I'm so sorry)
8
4,509
How did I write a 25,000-word review of iOS 27 in two weeks?
I did it all thanks to @NotionHQ and my custom local AI research setup with @jundotkim's oMLX.
Here's my story on how I ran local agents for 3 months to make it happen.
macstories.net/club/how-i-us…
6
4
61
7,415
Get your Apple Reminders in Claude Code.
RemCTL 2.1.0 now ships with a Claude Code plugin and mod, so you can always see what's left to do today, or in a specific list. There's even a sidebar!
Get the update here: github.com/viticci/remctl
@amorriscode
You can now mod Claude Code:
- Change how it behaves
- Customize the UI
- Swap in your own features
Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app.
A few examples:
14
8
141
18,036
In this week's episode of our portable gaming podcast, NPC:
- The rarest handheld with only 20 (!?) of them made
- More on the @anbernic_china RG DS Plus
piped.video/watch?v=XtuVnyb6…
2
2,785
Federico Viticci retweeted
Unfortunate Dot discovery:
They can only connect to one computer at a time from the computer they connect to.
So connecting to my desktop and server Macs requires jumping. back and forth to authorize them as needed.
1
1
6
1,913
How do different agents compare in terms of answering a question to a very recent problem?
I asked: how can I enable T3 Code 'Sign in with ChatGPT' for my Business account? (You can't right now; Plus and Pro only.)
The answer requires checking two different OpenAI support docs updated yesterday.
- Muse: got it completely wrong and hallucinated a URL
- Grok Bot: better, but failed to find the root cause of the issue
- Claude's new Projects, Opus 5.5 High: gave a technical explanation that's not possible at all right now
- Claude Cowork, Sonnet 5.5 High: a better answer than Projects with the correct Business caveat.
- ChatGPT Work, Sol 6.1 Light: perfect answer. Short and factual.
- Hermes Agent, Opus 5.5 High: another perfect answer, even found a related thread on X
- Open Minis, Astra Medium: good answer, factually correct. More verbose compared to Sol 6.1 in Work.
Lesson: the model matters, but the harness around it matters a whole lot more for these products. Usually, when you're getting fast answers, the trade-off is accuracy and laziness.
I'm bummed that I can't test Dots in Europe. I hope we get that, plus Sol 6.1 Ultrafast, soon.
10
2
49
7,470
