Show HN: Apfel – The free AI already on your Mac
203 points
3 hours ago
| 12 comments
| apfel.franzai.com
| HN
convexly
9 minutes ago
[-]
I like the approach of running everything locally. I'm strongly of the opinion that the privacy angle for local models is going to keep getting stronger and more relevant. The amount of articles that come out about accidents happening because of people handing too much context to cloud models the more self reinforcing this will become.
reply
brians
1 hour ago
[-]
I’ve seen several projects like this that offer a network server with access to these Apple models. The danger is when they expose that, even on a loop port, to every other application on your system, including the browser. Random webpages are now shipping with JavaScript that will post to that port. Same-origin restrictions will stop data flow back to the webpage, but that doesn’t stop them from issuing commands to make changes.

Some such projects use CORS to allow read back as well. I haven’t read Apfel’s code yet, but I’m registering the experiment before performing it.

reply
brians
59 minutes ago
[-]
They offer it as an option but default it to false! This is still a --footgun option but it’s the least unsafe version I’ve seen yet! Well done, Apfel authors.
reply
robotswantdata
17 minutes ago
[-]
Keep seeing similar mistakes with vibe coded AI & MCP projects. Even experienced engineers seem oblivious to this attack vector
reply
stingraycharles
1 hour ago
[-]
I don’t think many browsers will allow posting to 127.0.0.1 from a random website. What’s the threat model here?
reply
layer8
7 minutes ago
[-]
Restricting such access it is still a work in progress: https://wicg.github.io/local-network-access/
reply
brians
58 minutes ago
[-]
I think any browser will allow it but not allow data read back.
reply
btown
8 minutes ago
[-]
FWIW this was the status quo (webpage could ping arbitrary ports but not read data, even with CORS protections) - but it is changing.

This is partially in response to https://localmess.github.io/ where Meta and Yandex pixel JS in websites would ping a localhost server run by their Android apps as a workaround to third-party cookie limits.

Chrome 142 launched a permission dialog: https://developer.chrome.com/blog/local-network-access

Edge 140 followed suit: https://support.microsoft.com/en-us/topic/control-a-website-...

And Firefox is in progress as well, though I couldn't find a clear announcement about rollout status: https://fosdem.org/2026/schedule/event/QCSKWL-firefox-local-...

So things are getting better! But there was a scarily long time where a rogue JS script could try to blindly poke at localhost servers with crafty payloads, hoping to find a common vulnerability and gain RCE or trigger exfiltration of data via other channels. I wouldn't be surprised if this had been used in the wild.

reply
airza
35 minutes ago
[-]
There is a CORS preflight check for POST requests that don't use form-encoding. It would be somewhat surprising if these weren't using JSON (though it wouldn't be that surprising if they were parsing submitted JSON instead of actually checking the MIME-type which would probably be bad anwyay)
reply
mememememememo
56 minutes ago
[-]
Isn't there a CORS preflight check for this? In most cases. I guess you could fashion an OG form to post form fields. But openai is probably a JSON body only.

The default scenario should be secure. If the local site sends permissive CORS headers bets may be off. I would need to check but https->http may be a blocker too even in that case. Unless the attack site is http.

reply
arendtio
2 minutes ago
[-]
For those who don't know, 'Apfel' is the German word for Apple.
reply
khalic
1 hour ago
[-]
AFM models are very impressive, but they’re not made for conversation, so keep your expectations down in chat mode.
reply
franze
3 hours ago
[-]
reply
swiftcoder
1 hour ago
[-]
Anyone tried using this as a sub-agent for a more capable model like Claude/Codex?
reply
khalic
29 minutes ago
[-]
If you’re looking into small models for tiny local tasks, you should try Qwen coder 0,5B. It’s more of an experiment, but it can output decent functions given the right context instructions.
reply
LatencyKills
1 hour ago
[-]
The combined (input/output) context window length is 4K. Claude would blow through that even when trying to read and summarize a small file.
reply
franze
1 hour ago
[-]
project started with

trying to run openclaw with it in ultra token saving mode, did totally not work.

great for shell scripts though (my major use case now)

reply
Oras
35 minutes ago
[-]
I like the idea and the clarity to explain the usage, my question would be: what kind of tasks it would be useful for?
reply
khalic
34 minutes ago
[-]
Making a sentence out of a json
reply
gigatexal
1 hour ago
[-]
It’s a very small model but I’ve been playing with it for some time now I’m impressed. Have we been sleeping on Apple’s models?

Imagine they baked Qwen 3.5 level stuff into the OS. Wow that’d be cool.

reply
bombcar
51 minutes ago
[-]
Apparently the Overcast guy build a beowulf cluster of Mac minis to use the Apple transcription service.

https://www.linkedin.com/posts/nathangathright_marco-arment-...

reply
FinnKuhn
9 minutes ago
[-]
For small tasks this seems perfect. However it being limited to English from what I can tell is quite a downsite for me.
reply
thenthenthen
1 hour ago
[-]
The vision models and OCR are SUPER
reply
elcritch
1 hour ago
[-]
Any know if these only installed on Tahoe? I'm running Sequoia still and get an error about model not found.
reply
HelloUsername
1 hour ago
[-]
> Apple Silicon Mac, macOS 26 Tahoe or newer, Apple Intelligence enabled
reply
p1anecrazy
2 hours ago
[-]
Really like demo cli tools description. Are they limited by the context window as well? What’s your experience with log file sizes?
reply
franze
2 hours ago
[-]
the 2 hard limits of Appel Intelligence Foundation Model and therefor apfel is the 4k token context window and the super hard guardrails (the model prefers to tell you nothing before it tells you something wrong ie ask it to describe a color)

parsing logfiles line by line, sure

parsing a whole logfile, well it must be tiny, logfile hardly ever are

reply
skrun_dev
3 hours ago
[-]
Notes.app handles big notebooks without choking on storage?
reply
ramon156
1 hour ago
[-]
Cool tool but I don't get why these websites make idiotic claims

> $0 cost

No kidding.

Why not just link the GH Github: https://github.com/Arthur-Ficial/apfel

reply
ffsm8
1 hour ago
[-]
reply