Show HN: NanoClaw – “Clawdbot” in 500 lines of TS with Apple container isolation

hebejebelus · 2026-02-01T23:29:17 1769988557

I think these days if I’m going to be actively promoting code I’ve created (with Claude, no shade for that), I’ll make sure to write the documentation, or at the very least the readme, by hand. The smell of LLM from the docs of any project puts me off even when I like the idea of the project itself, as in this case. It’s hard to describe why - maybe it feels like if you care enough to promote it, you should care to try and actually communicate, person to person, to the human being promoted at. Dunno, just my 2c and maybe just my own preference. I’d rather read a typo-ridden five line readme explaining the problem the code is there to solve for you and me,the humans, not dozens of lines of perfectly penned marketing with just the right number of emoji. We all know how easy it is to write code these days. Maybe use some of that extra time to communicate with the humans. I dunno.

Edit: I see you, making edits to the readme to make it sound more human-written since I commented ;) https://github.com/gavrielc/nanoclaw/commit/40d41542d2f335a0...

jimminyx · 2026-02-02T00:19:13 1769991553

OP here. Appreciate your perspective but I don't really accept the framing, which feels like it's implying that I've been caught out for writing and coding with AI.

I don't make any attempt to hide it. Nearly every commit message says "Co-Authored-By: Claude Opus 4.5". You correctly pointed out that there were some AI smells in the writing, so I removed them, just like I correct typos, and the writing is now better.

I don't care deeply about this code. It's not a masterpiece. It's functional code that is very useful to me. I'm sharing it because I think it can be useful to other people. Not as production code but as a reference or starting point they can use to build (collaboratively with claude code) functional custom software for themselves.

I spent a weekend giving instructions to coding agents to build this. I put time and effort into the architecture, especially in relation to security. I chose to post while it's still rough because I need to close out my work on it for now - can't keep going down this rabbit hole the whole week :) I hope it will be useful to others.

BTW, I know the readme irked you but if you read it I promise it will make a lot more sense where this project is coming from ;)

furyofantares · 2026-02-02T04:00:15 1770004815

The problem with LLM-written is that I run into so many README.md's where it's clear the author barely read the thing they're expecting me to read and it's got errors that waste my time and energy.

I don't mind it if I have good reason to believe the author actually read the docs, but that's hard to know from someone I don't know on the internet. So I actually really appreciate if you are editing the docs to make them sound more human written.

MrJohz · 2026-02-02T10:07:50 1770026870

I think the other aspect is that if the README feels autogenerated without proper review, then my assumption is that the code is autogenerated without proper review as well. And I think that's fine for some things, but if I'm looking at a repo and trying to figure out if it's likely to work, then a lack of proper review is a big signal that the tool is probably going to fall apart pretty quickly if I try and do something that the author didn't expect.

nialse · 2026-02-02T06:27:58 1770013678

”I don't care deeply about this code. It's not a masterpiece. It's functional code that is very useful to me.” - AI software engineering in a nutshell. Leaving the human artisan era of code behind. Function over form. Substance over style. Getting stuff done.

_zoltan_ · 2026-02-02T07:37:09 1770017829

There should never have been an "artisan era". We use computers to solve problems. You should have always getting stuff done instead of bikeshedding over nitty-gritty details, like when in the office people have been spending weeks on optimizing code... just to have the exact same output, exact same time, but now "nicer".

You get paid to get stuff done, period.

EagnaIonat · 2026-02-02T09:10:21 1770023421

> just to have the exact same output, exact same time, but now "nicer".

The majority of code work is maintaining someone else's code. That's the reason it is "nicer".

There is also the matter of performance and reducing redundancy.

Two recent pulls I saw where it was AI generated did neither. Both attempted to recreate from scratch rather than using industry tested modules. One was using csv instead of polars for the intensive work.

So while they worked, they became an unmaintainable mess.

mchaver · 2026-02-02T09:19:30 1770023970

> There should never have been an "artisan era".

Firm no. There should be and there will continue to be. Maybe for you all code is business/money-making code, but that is not true for everyone.

> We use computers to solve problems.

We can use computers for lots of things like having fun, making art, and even creating problems for other people.

> You get paid to get stuff done, period.

That is a strange assumption. Plenty of people are writing code without being paid for it.

frizlab · 2026-02-02T08:32:33 1770021153

Yeah. Exactly the same as there should never be an “artisan era” for chairs, tables, buildings, etc.

Hell even art! Why should art even be a thing? We are machine driven by neurons, feelings do not exist.

Might be your life, it ain’t mine. I’m an artisan of code, and I’m proud to be one. I might finally use AI one of these days at work because I’ll have to, but I’ll never stop cherishing doing hand-crafted code.

codeforclout · 2026-02-02T07:24:32 1770017072

Was about to comment precisely this, that line does not inspire any confidence.

And it reminds me of a comment I saw in a thread 2 days ago. One about how RAPIDLY ITERATIVE the environment is now. There area lot of weekend projects being made over the knee of a robot nowadays and then instantly shared. Even OpenClaw is to a great extent, an example of that at its current age. Which comes in contrast to the length of time it used to take to get these small projects off the ground in the past. And also in contrast with how much code gets abandoned before and after "public release.

I'm looking at AI evangelists and I know they're largely correct about AI. I also look at what the heck they built, and either they're selling me something AI related, or have a bunch of defunct one-shot babies or mostly tools so limited in scope they server only themselves with it. We used to have a filter for these things. Salesmen always sold promises, so, no change there, just the buzzwords. But the cloutchasers? Those were way smaller in number. People building the "thing" so the "thing" exists mostly stopped before we ever heard of the "thing", because, turns out, caring about the "thing" does not actually translate to the motivation to getting it done. Or Maintain it.

What we have now is a reverse survivorship bias.

OOP stating they don't care about the state of their code during their public release, means I must assume they're a Cloutchaser. Either they don't care because they know they can do better which means they shared something that isn't their best, so their motivation with the comment is to highlight the idea. They just wanted to be first. Clout. Or they don't exactly concern with if they can as they just don't care about code in general and just want the product, be it good or be it not. They believe in the idea enough they want to ensure it exists, regardless of what's in the pudding. Which means to me, they also don't care to understand what's in the ingredient list. Which means they aren't best to maintain it. And that latter is the kind that, before the LLM slop was a concept in our minds, were precisely ones among the people who would give up half way through Making The "Thing".

See you in 16 weeks OP. I'll eat my shoe then.

vasco · 2026-02-02T07:18:24 1770016704

The art department is that way, we do engineering here. Faster is better.

figassis · 2026-02-02T07:41:14 1770018074

What part of faster is better means engineering to you? Non engineers will prefer you get there faster, but however you get there, better is better.

vasco · 2026-02-02T08:08:26 1770019706

If you want to say something just say it no need for trap questions.

Faster delivery of a project being better for engineering is obviously one of the most important things because it gives you back time to invest in other parts of your project. All engineering is trade-offs. Being faster at developing basic code is better, the end. If nothing else you can now spend more time on requirements and on a second iteration with your customer.

frizlab · 2026-02-02T08:35:00 1770021300

> obviously one of the most important things because it gives you back time to invest in other parts of your project

That is until you get so deep in code debt that you cannot move anymore.

There is an equilibrium to be found. Faster is not always better, and trying to have every single line perfect is not good either.

vasco · 2026-02-02T10:08:23 1770026903

I did mention trade offs.

hebejebelus · 2026-02-02T00:33:52 1769992432

Hey, you do you, I’m glad you appreciate my perspective. I wasn’t trying to catch you out but I see how it came across that way - I apologise for my edit, I had hoped the ;) would show that I meant it in jest rather than in meanness but I shouldn’t have added it in the first place.

As I said in my comment, no shade for writing the code with Claude. I do it too, every day.

I wasn’t “irked” by the readme, and I did read it. But it didn’t give me a sense that you had put in “time and effort” because it felt deeply LLM-authored, and my comment was trying to explore that and how it made me feel. I had little meaningful data on whether you put in that effort because the readme - the only thing I could really judge the project by - sounded vibe coded too. And if I can’t tell if there has been care put into something like the readme how can I tell if there’s been care put into any part of the project? If there has and if that matters - say, I put care into this and that’s why I’m doing a show HN about it - then it should be evident and not hidden behind a wall of LLM-speak! Or at least; that’s what I think. As I said in a sibling comment, maybe I’m already a dinosaur and this entire topic won’t matter in a few years anyway.

anavat · 2026-02-02T06:03:23 1770012203

There needs to be a word for the feeling of sudden realization that you're reading an AI-generated text (or watching an AI-generated video) where you expected it to be human-authored.

ultra2d · 2026-02-02T08:03:54 1770019434

AI erlebnis.

snovv_crash · 2026-02-02T07:02:05 1770015725

Uncanny valley

cess11 · 2026-02-02T07:54:58 1770018898

Slopstricken.

patcon · 2026-02-02T05:24:50 1770009890

Strongly agree with your comments.

yunohn · 2026-02-02T07:57:03 1770019023

For example - I checked src/, and there’s clearly more than ~500 lines of code, ignoring the other dirs. I’m on mobile, maybe someone else can run wc -l on the repo and confirm. Is there a reason this number is inaccurately stated? Immediately makes me wary of the vibe coded nature of it.

jofzar · 2026-02-02T02:50:17 1770000617

I 100% agree, reading very obviously ai written blogs and "product pages"/readme's has turned into a real ick for me.

Just something that screams "I don't care about my product/readme page, why should you".

To be clear, no issue with using AI to write the actual program/whatever it is. It's just the readme/product page which super turns me off even trying/looking into it.

charcircuit · 2026-02-02T07:16:49 1770016609

Why do you think people do not care about something if they AI generated it? I care about many things I've generated.

wernsey · 2026-02-02T08:55:31 1770022531

It's the perception.

"I couldn't be bothered to write a proper README, so I had the AI do it"

charcircuit · 2026-02-02T09:54:30 1770026070

AI can write a proper README. In fact, it's better than me at doing so and keeping it up to date. People writing README with AI are bothering to write it. In my experience AI won't automatically create README files for you when making projects with the exception of create project tools which create a default README, but in that case usually the AI ignores it and leaves it in the default state. People are just using a tool that lets them create without manually typing in each individual character.

pseudony · 2026-02-02T09:54:48 1770026088

FWIW, this is a variation of the age-old thing about open source.

It isn’t “have it your way”, he graciously made code available, use it or leave it.

iterateoften · 2026-02-01T23:35:19 1769988919

Project releases with llms have grown to be less about the functionality and more about convincing others to care.

Before the proof of work of code in a repo by default was a signal of a lot of thought going into something. Now this flood of code in these vibe coded projects is by default cheap and borderline meaningless. Not throwing shade or anything at coding assistants. Just the way it goes

101008 · 2026-02-01T23:40:28 1769989228

I agree 100% with you. It's even worse though. They haven't checked if the Readme has hallucinated it or not (spoiler: it has):

https://news.ycombinator.com/item?id=46850317

hebejebelus · 2026-02-01T23:48:41 1769989721

I don’t want to come off like I’m shitting on the poster here. I’ve definitely made that kind of careless mistake, probably a dozen times this week. And maybe we’re heading to a future where nobody even reads the readme anymore because they won’t be needed because an agent can just conjure one from the source code at will, so maybe it actually straight up doesn’t matter. I’ve just been thinking about what it means to release software nowadays, and I think the window for releasing software for clout and credit is closing, since creating software basically requires a Claude subscription and an idea now, so fewer people are impressed by the thing simply existing, and the standard of care for a project released for that aim (of clout) needs to be higher than it maybe needed to be in the past. But who knows, I’m probably already a dinosaur in today’s world, and I really don’t mean to shit on the OP - it’s a good idea for a project and it makes a lot of sense for it to exist. I just can’t tell if any actual care has gone into it, and if not, why promote?

isodev · 2026-02-02T07:05:33 1770015933

> I don’t want to come off like I’m shitting on the poster

Why not, if they're making people read AI slop without checking it first? They deserve the shit-nudge to fix it.

roysting · 2026-02-02T09:48:37 1770025717

That seems like a fair perspective; OP “shit” AI Slop on us so the minimum the project deserves is being shit on for making people look at his unreviewed sloppy project without at least warning about it being unreviewed.

Just consider what a bigger AI shit show vortex we are looking at, where this project only exists because of other ill considered AI slop projects. But at the same time, AI is not going anywhere and it does have the potential to massively “improve” things.

I believe it’s really just that we are going through adaptation pains, with everyone really just being sloppy for all the same kinds of reasons that people were sloppy before AI. It’s not like even the biggest corporations didn’t create sloppy messes before AI. Microsoft is a canonical example of this whole notion for basically its whole existence; poorly conceived, sloppily executed, even its core product line being so inherently insecure that it has not just spun up its own separate sectors of industries, but multiple sectors of industries around patching the security sieve called Microsoft, something akin to a monopoly on plumbing created from wire mesh.

It is making me think of how to increase the quality of my QA and final review process though. But frankly, I think we will soon fondly reminisce about a time when AI still produced slop and a human was actually useful and even needed to do QA and final review; as bleak as that sounds. I don’t see how that will not be the case within two years from now, and that’s probably being generous, as fast as things have been developing.

muyuu · 2026-02-02T07:45:54 1770018354

the main reason I'd want a person to write or at least curate readmes is because models have, at least for the time being, this tendency to make confident and plausible-sounding claims that are completely false (hallucination applied to claims on the stuff they just made)

so long as this is commonplace I'd be extremely sceptical of anything with some LLM-style readmes and docs

the caveats to this is that LLMs can be trained to fool people with human-sounding and imperfectly written readmes, and that although humans can quickly oversee that things compile and seem to produce the expected outputs, there's deeper stuff like security issues and subtle userspace-breaking changes

track-record is going to see its importance redoubled

raahelb · 2026-02-02T09:02:05 1770022925

You will definitely like Josh Mock's recent post: https://joshmock.com/post/2026-agents-md-as-a-dark-signal/

roysting · 2026-02-02T09:59:43 1770026383

I am confused by “senior-learning engineer”; so he’s learning as a senior, learning at a “senior” level in a “continuous learning”, “life long learning” kind of way? What is senior-learning? Searching for it only comes up with learning for seniors programs.

swyx · 2026-02-02T08:40:04 1770021604

orrrr you could go the other way and read explicitly ai-generated docs that use the code as source of truth https://deepwiki.com/gavrielc/nanoclaw

jstanley · 2026-02-02T10:17:01 1770027421

Cool idea but I just tried it out on one of my own repos and I couldn't get past the reCAPTCHA, maybe remove that.

(I'm a human btw)

raincole · 2026-02-02T06:28:38 1770013718

> I’d rather read a typo-ridden five line readme explaining the problem the code is there to solve for you and me,the humans, not dozens of lines of perfectly penned marketing with just the right number of emoji

Don't worry, bro. If enough people are like you, there will be fully automatic workflow to add typos into AI writing.

Nevermark · 2026-02-02T07:06:18 1770015978

As a practical matter, if it tones down the AI sleuthing vs. reading, it might be a good idea.

Assuming the written/generated text is well written/generated, of course.

popcorncowboy · 2026-02-02T00:24:58 1769991898

> running it scares the crap out of me

A hundred times this. It's fine until it isn't. And jacking these Claws into shared conversation spaces is quite literally pushing the afterburners to max on simonw's lethal trifecta. A lot of people are going to get burned hard by this. Every blackhat is eyes-on this right now - we're literally giving a drunk robot the keys to everything.

charcircuit · 2026-02-02T07:37:27 1770017847

It turns out the lethal trifecta is not so lethal. Should a business avoid hiring employees since technically employees can steal from the cash register. The lethal trifecta is about binary security. Either the data can be taken or it can't. This may be overly cautious. It may be possible that hiring an employee has a positive expected value when when you account for the possibility of one stealing from the cash register.

naruhodo · 2026-02-02T08:06:13 1770019573

Employees are humans and therefore subject to the law. There are remedies. And you can point a camera at the cash register.

Who are you going to arrest and/or sue when you run a chat bot "at your own risk" and it shoots you in the foot?

charcircuit · 2026-02-02T08:11:23 1770019883

If your chatbot provided you 1.5 feet worth of value before shooting your foot it may have been worth it. The optimal self damage to maximize total value may be non 0.

p0nce · 2026-02-02T09:15:51 1770023751

If you peruse molthub and moltbook you'll see the agents have already built six or seven such social networks. It is terrifying.

anabis · 2026-02-02T01:44:11 1769996651

Maybe. People have run wildly insecure phpBB and Wordpress plugins, so maybe its the same cycle again.

egeozcan · 2026-02-02T02:31:58 1769999518

Those usually didn't have keys to all your data. Worst case, you lost your server, and perhaps you hosted your emails there too? Very bad, but nothing compared to the access these clawdbot instances get.

Terretta · 2026-02-02T03:58:48 1770004728

> Those usually didn't have keys to all your data.

As a former (bespoke) WP hosting provider, I'd counter those usually did. Not sure I ever met a prospective "online" business customer's build that didn't? They'd put their entire business into WP installs with plugins for everything.

Our step one was to turn WP into static site gen and get WP itself behind a firewall and VPN, and even then single tenant only on isolated networks per tenant.

To be fair that data wasn't ALL about everyone's PII — until by ~2008 when the Buddy Press craze was hot. And that was much more difficult to keep safe.

DANmode · 2026-02-02T01:57:17 1769997437

> are running

TacticalCoder · 2026-02-02T01:04:18 1769994258

I understand that things can go wrong and there can be security issues, but I see at least two other issues:

1. what if, ChadGPT style, ads are added to the answers (like OpenAI said it'd do, hence the new "ChadGPT" name)?

2. what if the current prices really are unsustainable and the thing goes 10x?

Are we living some golden age where we can both query LLMs on the cheap and not get ad-infected answers?

I read several comments in different threads made by people saying: "I use AI because search results are too polluted and the Web is unusable"

And I now do the same:

"Gemini, compare me the HP Z640 and HP Z840 workstations, list the features in a table" / "Find me which Xeon CPU they support, list me the date and price of these CPU when they were new and typical price used now".

How long before I get twelve ads along with paid vendors recommendations?

spiderice · 2026-02-02T01:49:18 1769996958

> what if the current prices really are unsustainable and the thing goes 10x?

Where does this idea come from? We know how much it costs to run LLMs. It's not like we're waiting to find out. AI companies aren't losing money on API tokens. What could possibly happen to make prices go 10x when they're already running at a profit? Claude Max might be a different story, but AI is going to get cheaper to run. Not randomly 10x for the same models.

overgard · 2026-02-02T02:35:00 1769999700

From what I've read, every major AI player is losing a (lot) of money on running LLMs, even just with inference. It's hard to say for sure because they don't publish the financials (or if they do, it tends to be obfuscated), but if the screws start being turned on investment dollars they not only have to increase the price of their current offerings (2x cost wouldn't shock me), but some of them also need a (massive) influx of capital to handle things like datacenter build obligations (10s of billions of dollars). So I don't think it's crazy to think that prices might go up quite a bit. We've already seen waves of it, like last summer when Cursor suddenly became a lot more expensive (or less functional, depending on your perspective)

raincole · 2026-02-02T06:46:41 1770014801

> From what I've read, every major AI player is losing a (lot) of money on running LLMs, even just with inference.

> It's hard to say for sure because they don't publish the financials (or if they do, it tends to be obfuscated)

Yeah, exactly. So how the hell the bloggers you read know AI players are losing money? Are they whistleblowers? Or they're pulling numbers out of their asses? Your choice.

sothatsit · 2026-02-02T04:29:10 1770006550

Dario Amodei has said that their models actually have a good return, even when accounting for training costs [0]. They lose money because of R&D, training the next bigger models, and I assume also investment in other areas like data centers.

Sam Altman has made similar statements, and Chinese companies also often serve their models very cheaply. All of this makes me believe them when they say they are profitable on API usage. Usage on the plans is a bit more unknown.

[0] https://youtu.be/GcqQ1ebBqkc?si=Vs2R4taIhj3uwIyj&t=1088

aeronaut80 · 2026-02-02T05:19:29 1770009569

Their whole company has to be profitable, or at least not run out of money/investors. If you have no cash you can't just point to one part of your business as being profitable, given that it will quickly become hopelessly out-of-date when other models overtake it.

sothatsit · 2026-02-02T05:53:24 1770011604

Yeah, that’s the whole game they’re playing. Compete until they can’t raise more and then they will start cutting costs and introducing new revenue sources like ads.

They spend money on growth and new models. At some point that will slow and then they’ll start to spend less on R&D and training. Competition means some may lose, but models will continue to be served.

hyperadvanced · 2026-02-02T02:59:23 1770001163

This is my understanding as well. If GPT made money the companies that run them would be publicly traded?

Furthermore, companies which are publicly traded show that overall the products are not economical. Meta and MSFT are great examples of this, though they have recently seen opposite sides of investors appraising their results. Notably, OpenAI and MSFT are more closely linked than any other Mag7 companies with an AI startup.

https://www.forbes.com/sites/phoebeliu/2025/11/10/openai-spe...

fragmede · 2026-02-02T03:39:47 1770003587

Going public is not a trivial thing for a company to do. You may want to bring in additional facts to support your thesis.

lemming · 2026-02-02T04:26:24 1770006384

Sam Altman is on record saying that OpenAI is profitable on inference. He might be lying, but it seems an unlikely thing to lie about.

up-n-atom · 2026-02-02T04:29:08 1770006548

Where did u get this notion from? you must not be old enough to know how subscription services play out. Ask your parents about their internet or mobile billings. Or the very least check Azures, AWS, Netflix historical pricing.

Heck we were spoiled by “memory is cheap” but here we are today wasting it at every expense as prices keep skyrocketing (ps they ain’t coming back down). If you can’t see the shift to forceful subscriptions via technologies guised as “security” ie. secure boot and the monopolistic distribution (Apple, Google, Amazon) or the OEM, you’re running with blinders. Computings future as it’s heading will be closed ecosystems that are subscription serviced, mobile only. They’ll nickel and dime users for every nuanced freedom of expression they can.

Is it crazy to correlate the price of memory to our ability to localize LLM?

raincole · 2026-02-02T06:36:23 1770014183

> Ask your parents about their internet or mobile billings. Or the very least check Azures, AWS, Netflix historical pricing.

None of these went 10x. Actually the internet went 0.0001~0.001x for me in terms of bits/money. I lived through dial-up era.

raincole · 2026-02-02T06:33:03 1770013983

> what if the current prices really are unsustainable and the thing goes 10x?

What if a thermonuclear war breaks out? What's your backup plan for this scenario?

I genuinely can't tell which is more likely to happen in the next decade. If I have to guess I'll say war.

crystaln · 2026-02-02T03:13:17 1770001997

Seems much more likely the cost will go down 99%. With open source models and architectural innovations, something like Claude will run on a local machine for free.

walterbell · 2026-02-02T05:00:36 1770008436

How much RAM and SSD will be needed by future local inference, to be competitive with present cloud inference?

FuckButtons · 2026-02-02T02:02:45 1769997765

I asked Gemini deep research to project when that will likely happen based on historical precedent. It guessed October 2027.

esskay · 2026-02-02T09:45:06 1770025506

Stupid stuff openclaw did for me:

- Created its own github account, then proceeded to get itself banned (I have no idea what it did, all it said was it created some new repos and opened issues, clearly it must've done a bit more than that to get banned)

- Signed up for a Gmail account using a pay as you go sim in an old android handset connected with ADB for sms reading, and again proceeded to get itself banned by hammering the crap out of the docs api

- Used approx $2k worth of Kimi tokens (Thankfully temporarily free on opencode) in the space of approx 48hrs.

Unless you can budget $1k a week, this thing is next to useless. Once these free offers end on models a lot of people will stop using it, it's obscene how many tokens it burns through, like monumentally stupid. A simple single request is over 250k chars every single time. That's not sustainable.

swordsith · 2026-02-02T10:18:43 1770027523

> and again proceeded to get itself banned by hammering the crap out of the docs api

> Used approx $2k worth of Kimi tokens

Holy shit dude you really should rethink your life decisions this is NUTS

reassess_blind · 2026-02-02T09:20:00 1770024000

What’s the difference between this, and just running Claude Code in —dangerously-skip-permissions mode in a container and accessing remotely via ssh?

I’m confused as to what these claw agents actually offer.

randomtoast · 2026-02-02T09:30:35 1770024635

The README.md describes it as:

WhatsApp (baileys) --> SQLite --> Polling loop --> Container (Claude Agent SDK) --> Response

So they basically put a Wrapper around Claude in a Container, which allows you to send messages from WhatsApp to Claude, and act somewhat as if you had a Siri on steriods.

reassess_blind · 2026-02-02T09:48:46 1770025726

Found the spec here: https://github.com/gavrielc/nanoclaw/blob/main/docs/SPEC.md

The scheduled tasks seem like the major functional difference. Pretty cool.

Has anyone tried Anthropic’s “Cowork”? How does that compare?

theptip · 2026-02-02T06:36:39 1770014199

> AI-native. No installation wizard; Claude Code guides setup. No monitoring dashboard; ask Claude what's happening. No debugging tools; describe the problem, Claude fixes it.

> Skills over features. Contributors shouldn't add features (e.g. support for Telegram) to the codebase. Instead, they contribute claude code skills like /add-telegram that transform your fork.

I’m interested to see how this model pans out. I can see benefits (don’t carry complexity you don’t need) and costs (how do I audit the generated code?).

But it seems pretty clear that things will move in this direction in ‘26 with all the vibe coding that folks are enjoying.

I do wonder if the end state is more like a very rich library of composable high-order abstractions, with Skills for how to use them - rather than raw skills with instructions for how to lossily reconstruct those things.

charcircuit · 2026-02-02T08:08:59 1770019739

I think the more interesting question is were tools the right abstraction. What is the implication of having only a single "shell" tool. Should the infinite possibilities to few happen by the AI having limited tools or should whatever the shell calls have the limitations applied there. Tools in a way are redundant.

thepoet · 2026-02-01T23:15:09 1769987709

One of the things that makes Clawdbot great is the allow all permissions to do anything. Not sure how those external actions with damaging consequences get sandboxed with this.

Apple containers have been great especially that each of them maps 1:1 to a dedicated lightweight VM. Except for a bug or two that appeared in the early releases, things seem to be working out well. I believe not a lot of projects are leveraging it.

A general code execution sandbox for AI code or otherwise that used Apple containers is https://github.com/instavm/coderunner It can be hooked to Claude code and others.

jckahn · 2026-02-02T00:06:51 1769990811

> One of the things that makes Clawdbot great is the allow all permissions to do anything.

Is this materially different than giving all files on your system 777 permissions?

the_fall · 2026-02-02T01:35:17 1769996117

> Is this materially different than giving all files on your system 777 permissions?

Yes, because I can't read or modify your files over the internet just because you chmod'ed them to 777. But with Clawdbot, I can!

smt88 · 2026-02-02T00:34:22 1769992462

It's vastly different.

It's more (exactly?) like pulling a .sh file hosted on someone else's website and running it as root, except the contents of the file are generated by a LLM, no one reads them, and the owner of the website can change them without your knowledge.

sheepscreek · 2026-02-02T01:43:11 1769996591

That was my line to the CS lab supervisor for handing me the superuser password. Guess what? He didn’t budge. Probably a good thing.

Lesson - never trust a sophomore who can’t even trust themselves (to get overly excited and throw caution to the wind).

Clawdbot is a 100 sophomores knocking on your door asking for the keys.

ivanstepanovftw · 2026-02-02T09:51:00 1770025860

Where are those 500 lines of code?

walterbell · 2026-02-02T04:49:58 1770007798

> found it useful but running it scares

https://maordayanofficial.medium.com/the-sovereign-ai-securi...

  At least 42,665 instances are publicly exposed on the internet, with 5,194 instances actively verified as vulnerable through systematic scanning..  The narrative that “running AI locally = security and privacy” is significantly undermined when 93% of deployments are critically vulnerable. Users may lose faith in self-hosted alternatives.. Governments and regulators already scrutinizing AI may use this incident to justify restrictions on self-hosted AI agents, citing security externalities.

dceddia · 2026-02-02T00:05:27 1769990727

This look nice! I was curious about being allowed to use a Claude Pro/Max subscription vs an API key, since there's been so much buzz about that lately, so I went looking for a solid answer.

Thankfully the official Agent SDK Quickstart guide says that you can: https://platform.claude.com/docs/en/agent-sdk/quickstart

In particular, this bit:

"After installing Claude Code onto your machine, run claude in your terminal and follow the prompts to authenticate. The SDK will use this authentication automatically."

joshstrange · 2026-02-02T01:46:10 1769996770

But their docs also say:

> Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead.

Which I have interpreted means that you can’t use your Claude code subscription with the agent SDK, only API tokens.

I really wish Anthropic would make it clear (and allow us to use our subscriptions with other tools).

ceroxylon · 2026-02-02T02:19:59 1769998799

Didn't Thariq make it clear three weeks ago when they shut down 3rd party tool access and the OpenCode users were upset?

> Third-party harnesses using Claude subscriptions create problems for users and are prohibited by our Terms of Service.

https://xcancel.com/trq212/status/2009689809875591565

swyx · 2026-02-02T08:41:40 1770021700

i think thats conflating two things (am not an expert). opencode exploited unauthorized use/api access, but obviously whatever that is using claude code sdk is kosher because its literally anthropic's blessed way to do this

thariq did a good intro here https://www.youtube.com/watch?v=TqC1qOfiVcQ

jimminyx · 2026-02-02T00:26:01 1769991961

OP here. Yes! This was a big motivation for me to try and build this. Nervous Anthropic is gonna shut down my account for using Clawdbot.

This project uses the Agents SDK so it should be kosher in regards to terms of service. I couldn't figure out how to get the SDK running inside the containers to properly use the authenticated session from the host machine so I went with a hacky way of injecting the oauth token into the container environment. It still should be above board for TOS but it's the one security flaw that I know about (malicious person in a WhatsApp group with you can prompt inject the agent to share the oauth key).

If anyone can help out with getting the authenticated session to work properly with the agents running in containers it would be much appreciated.

dceddia · 2026-02-02T01:17:09 1769995029

I went down this rabbit hole a bit recently trying to use claude inside fence[0] and it seems that on macOS, claude stores this token inside Keychain. I'm not sure there's a way to expose that to a container... my guess would be no, especially since it seems the container is Linux, and also because keeping the Keychain out of reach of containers seems like it would be paramount. But someone might know better!

0: https://github.com/Use-Tusk/fence

gronky_ · 2026-02-02T01:22:30 1769995350

True. There’s a setting for Claude code though where you can add apiKeyHelper which is a script you add that gets the token for Claude Code. I imagine you can use that but haven’t quite figured out how to wire it up

hebejebelus · 2026-02-02T00:11:42 1769991102

Wow, thanks for posting that, news to me! In this case I don’t understand why there was a whole brouhaha with OpenClaw and the like - I guess they were invoking it without the official SDK? Because this makes it seem like if you have the sub you can build any agentic thing you like and still use your subscription, as long as you can install and login to Claude code on the machine running it.

disillusioned · 2026-02-02T00:13:38 1769991218

Tons of chatter on Twitter making it sound like you'll get permabanned for doing this but... 1) how would they know if my requests are originating from Claude Code vs. OpenClaw? 2) how are we violating... anything? I'm working within my usage limits...

$70 or whatever to check if there's milk... just use your Claude Max subscription.

zarzavat · 2026-02-02T00:24:46 1769991886

> how would they know if my requests are originating from Claude Code vs. OpenClaw

How wouldn't they know? Claude Code is proprietary they can put whatever telemetry they want in there.

> how are we violating... anything? I'm working within my usage limits...

It's well known that Claude code is heavily discounted compared to market API rates. The best interpretation of this is that it's a kind of marketing for their API. If you are not using Claude code for what it's intended for, then it's violating at least the spirit of that deal.

cypherpunks01 · 2026-02-02T05:09:25 1770008965

Hate to ask the obvious question but.. how does Claude check for milk?

dceddia · 2026-02-02T01:31:17 1769995877

The Claude Code client adds system prompts and makes a bunch of calls to analytics/telemetry endpoints so it's certainly feasible for them to tell, if they inspect the content of the requests and do any correlation between those services.

And apparently it's violating the terms of service. Is it fair and above board for them to ban people? idk, it feels pretty blatantly like control for the sake of control, or control for the sake of lock-in, or those analytics/telemetry contain something awfully juicy, because they're already getting the entire prompt. It's their service to run as they wish, but it's not a pro-customer move and I think it's priming people to jump ship if another model takes the lead.

firloop · 2026-02-02T00:12:44 1769991164

Was there a brouhaha with OpenClaw or was that with OpenCode?

disillusioned · 2026-02-02T00:23:30 1769991810

It was with OpenCode, but a LOT of the commentariat is insisting that running OpenClaw through subscription creds instead of API is out of TOS and will get you banhammered.

hebejebelus · 2026-02-02T00:14:20 1769991260

I think you’re right and it was OpenCode. The semantic collisions are going to becpme more of a problem in the coming Cambrian explosion of software

aitchnyu · 2026-02-02T08:57:53 1770022673

That Baileys api for Whatsapp may (AFAICT) put you in thin ice with Meta. Is there a cheap legit alternative?

https://baileys.wiki/docs/intro/

dandaka · 2026-02-02T09:16:45 1770023805

I was using WAHA. It is an abstraction layer with a proper API on top. It supports many engines like Baileys and Whatsmeow (golang).

Unfortunately, all those solutions are shaky and could lead to a ban on your account.

https://waha.devlike.pro/

narmiouh · 2026-02-02T00:48:37 1769993317

I feel like a lot of non technical people who are vibe coding or vibe using these models, focus on hallucinations and believe that as the hallucinations are reduced in benchmarks, and over estimate their ability to create safe prompts that will keep these models in line.

I think most people fail to estimate the real threat that malicious prompts can cause because it is not that common, its like when credit cards were launched, cc fraud and the various ways it could be perpetrated followed not soon after. The real threats aren’t visible yet but rest assured there are actors working to take advantage and many unfortunate examples will be seen before general awareness and precaution will prevail….

prophesi · 2026-02-02T05:48:21 1770011301

Am I correct that after cloning down the project, you open the directory in Claude Code, then "execute" a markdown file instructing a nondeterministic LLM to set everything up for you in natural language?

te_chris · 2026-02-02T05:50:59 1770011459

Posthog is doing this now for project setup

nsonha · 2026-02-02T06:09:40 1770012580

Not sure if this is meant to be sarcastic but isn't Posthog patient zero of Sha1-Hulud 2.0?

prophesi · 2026-02-02T08:27:20 1770020840

It's certainly a good time to get into cybersecurity.

mark_l_watson · 2026-02-01T23:25:50 1769988350

I like the idea of a smaller version of OpenClaw.

Minor nitpick, it looks like about 2500 lines of typescript (I am on a mobile device, so my LOC estimate may be off). Also, Apple container looks really interesting.

sothatsit · 2026-02-02T04:39:21 1770007161

The idea of avoiding config files, and having the config be getting your agent to modify its own codebase, is fascinating.

My gut reaction says that I don't like it, but it is such an interesting idea to think about.

treelover · 2026-02-01T23:19:52 1769987992

Interesting choice to use native Apple Containers over Docker.

I assume this is to keep the footprint minimal on a Mac Mini without the overhead of the Docker VM, but does this limit the agent's ability to run standard Linux tooling? Or are you relying on the AI to just figure out the BSD/macOS equivalents of standard commands?

garblegarble · 2026-02-02T10:08:34 1770026914

>does this limit the agent's ability to run standard Linux tooling? Or are you relying on the AI to just figure out the BSD/macOS equivalents of standard commands?

Slightly counterintuitively, Apple Containers spawns linux VMs.

There doesn't appear to be any way to spawn a native macOS container... which is a pity, it'd be nice to have ultra-low-overhead containers on macOS (but I suspect all the interesting macOS stuff relies on a bunch of services/gui access that'd make it not-lightweight anyway)

FYI: it's easy enough to install GNU tools with homebrew; technically there's a risk of problems if applications spawn commandline tools and expect the BSD args/output but I've not run into any issues in the several years I've been doing it).

ohyoutravel · 2026-02-01T23:24:30 1769988270

[flagged]

reassess_blind · 2026-02-02T00:59:36 1769993976

What makes you think it's an AI comment?

yomismoaqui · 2026-02-02T01:26:50 1769995610

Maybe what you are responding to is the AI comment? Or am I?

cadamsdotcom · 2026-02-02T00:27:53 1769992073

If only there were some way to answer your own question. Maybe with some kind of engine that searches.

selkin · 2026-02-02T02:25:01 1769999101

Not sure if it's intended, but Apple Container is a microvm, providing mich better isolation than containers (while retaining the familiar interface)

TheDong · 2026-02-02T05:41:22 1770010882

"much better isolation than containers"

If you've got an exploit for docker / linux containers, please share it with the class.

What I'm saying is that in practice, containers and VMs have both been quite secure.

Also, you can configure docker to run microvms too https://github.com/firecracker-microvm/firecracker-container...

eskaytwo · 2026-02-02T00:56:26 1769993786

Thanks! Was hoping someone would do something more sane like this.

Openclaw is very useful, but like you I share the sentiment of it being terrifying, even before you introduce the social network aspect.

My Mac mini is currently literally switched off for this very reason.

avaer · 2026-02-01T23:07:37 1769987257

  Quick Start
  git clone https://github.com/anthropics/nanoclaw.git

Is this an official Anthropic project? Because that repo doesn't exist.

Or is this just so hastily thrown together that the Quick Start is a hallucination?

That's not a facetious question, given this project's declared raison d'etre is security and the subtle implication that OpenClaw is an insecure unreviewed pile of slop.

jimminyx · 2026-02-01T23:22:25 1769988145

Fixed, thanks. Claude Code likes to insert itself and anthropic everywhere.

If it somehow wasn't abundantly clear: this is a vibe coded weekend project by a single developer (me).

It's rough around the edges but it fits my needs (talking with claude code that's mounted on my obsidian vault and easily scheduling cron jobs through whatsapp). And I feel a lot better running this than a +350k LOC project that I can't even begin to wrap my head around how it works.

This is not supposed to be something other people run as is, but hopefully a solid starting point for creating your own custom setup.

kklisura · 2026-02-01T23:19:24 1769987964

Claude hallucinated that repo here in this commit https://github.com/gavrielc/nanoclaw/commit/dbf39a9484d9c66b...

mcintyre1994 · 2026-02-01T23:22:50 1769988170

I like that Claude's hypothesis was that Anthropic created openclaw and this anti-openclaw :)

> This is the anti-[OpenClaw](https://github.com/anthropics/openclaw).

raybb · 2026-02-01T23:10:05 1769987405

Seems to be fixed now

renewiltord · 2026-02-01T23:32:03 1769988723

To be honest, when I see many vibecoded apps, I just build my own duplicate with Claude Code. It's not that useful to use someone else's vibecode. The idea is enough, or the evidence that it works for someone else means I can just build it myself with Claude Code and I can make it specific to my needs.

sanex · 2026-02-02T03:34:32 1770003272

Yes exactly! Even non vibe coded libraries I think are losing their value as the cost of writing and maintaining your code goes to zero. Supply chain attacks are gone, no risk of license changes. No bloat from code you don't use. The code is the documentation and the configuration. The vibes are the package manager. That's why I like this version over openclaw. I can fork it as a starting point or just give it to Claude for inspiration but either way I'm getting something tailored exactly to me.

dsrtslnd23 · 2026-02-02T06:31:31 1770013891

can NanoClaw be used to participate in ClackerNews?

Tepix · 2026-02-02T06:54:26 1770015266

A personal assistant that runs in the standard cloud (anthropic in this case) is madness. That‘s the hill I‘m willing to die on. Run it locally or use a cloud provider you can deeply trust.

ed_mercer · 2026-02-02T00:51:31 1769993491

If you run openclaw on a spare laptop or VM and give it read only access to whatever it needs, doesn’t that eliminate most of the risk?

AlexCoventry · 2026-02-02T00:58:17 1769993897

If you're letting it communicate with the outside world, you risk the leak and abuse of anything sensitive in the data it has access to.

ttul · 2026-02-02T02:42:47 1770000167

s/risk/guarantee (given sufficient time)/

Johnny_Bonk · 2026-02-01T23:48:49 1769989729

Can you use MCP tools? I saw that with open claw they moved away from that which I personally didn't like but

johntash · 2026-02-02T00:06:41 1769990801

I somewhat like the idea of not using MCP as much as it is being hyped.

It's certainly helpful for some things, but at the same time - I would rather improved CLI tools get created that can be used by humans and llm tools alike.

CuriouslyC · 2026-02-02T00:41:54 1769992914

It uses a wrapper in places to consume MCPs as clis.

Bnjoroge · 2026-02-02T01:24:02 1769995442

Can we start putting disclaimers beside the title on AI-generated projects? Extremely fatiguing to read through it and realize it’s mostly LLM slop.

chaostheory · 2026-02-02T07:47:53 1770018473

For anyone else worried about running openclaw, in my case I just bought openclaw its Mac mini and I gave openclaw its own accounts including GitHub. It makes many of the security concerns moot. Of course, I could go further and give openclaw its own internet access as well.

suprstarrd · 2026-02-02T01:33:15 1769995995

It blows my mind that this wasn't the thought process going in. Thank you for doing this!

singular_atomic · 2026-02-02T03:05:18 1770001518

Hackernews needs a mute keywords feature. Clawd/molt-slop is mass AI psychosis on steroids.

fragmede · 2026-02-02T07:17:13 1770016633

If only there was some sort of thing that would help you build that for yourself.

cyanydeez · 2026-02-01T23:02:28 1769986948

The singularity, but instead successive exponential improvement, its excessive exponential slop which passes the Turing test for programmers.

nsonha · 2026-02-02T03:47:56 1770004076

what's the difference between this and just exposing opencode running in colima or whatever through tailscale? I got the impression that Clawdbot adds the headless browser (does it?) and that's the value. Otherwise even "nano"claw seems like uneccessary bloat for me.

aaronbrethorst · 2026-02-01T23:02:46 1769986966

lol, I might finally have to upgrade my Mac mini to Tahoe. Yofi.