Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

github.com

Post reply on HN
Print view View original

221–230 of 239 posts

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

#221

Post by furyofantares »

laksjhdlka wrote: post #220
furyofantares wrote: post #73

Earlier quoted context omitted.

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 the…

The README is for your agent to read. Shrug.

The agent having incorrect documentation in its context is really bad!

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

#222

Post by srinath693 »

The "skills not features" contribution model is the most interesting part of this. Instead of a project that grows into another 52-module beast, contributors teach Claude how to transform the codebase per-user. It's basically contributing build instructions instead of build artifacts. If it actually works in practice, it's a genuinely novel approach to keeping small projects small.

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

#223

Post by DavideNL »

dceddia wrote: post #46
jimminyx wrote: post #34

Earlier quoted context omitted.

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 int…

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: http…

> "I went down this rabbit hole a bit recently trying to use claude inside fence[0]"

Did you get it working in the end? I assume you didn't share your setup/config anywhere?

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

#224

Post by FreePalestine1 »

ramoz wrote: post #192

Not seeing how the sandbox prevents anything really. The point of OpenClaw is to connect out to different systems.

Sure but at least it protects against unauthorized free-for-all access on your host system. If you want to explicitly give it access to external APIs over the internet that's a risk you personally are taking. It's really smart to run something like this in a sandbox, especially in the current beta/experimentation phase.

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

#225

Post by vasco »

swiftcoder wrote: post #176
vasco wrote: post #103

Earlier quoted context omitted.

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

> we do engineering here Well, we make software, at any rate. Most of the time that's pretty divorced from capital-E engineering, which is why we get to be cavalier about the quality of the result - let me know how you feel about the bridges and tunnels you drive on being built "as fast as possible, to hell with safety"

Don't put words in my mouth, you don't care about safety not me. And for what it's worth I'm an electrical engineer first, so if you have some inferiority complex about software you don't have to apply it to me.

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

#227

Post by swiftcoder »

vasco wrote: post #225
swiftcoder wrote: post #176

Earlier quoted context omitted.

> we do engineering here Well, we make software, at any rate. Most of the time that's pretty divorced from capital-E engineering, which is why we get to be cavalier about the quality of the result - let me know how you feel about the bridges and tunnels you drive on being built "as fast as possible, to hell with safety"

Don't put words in my mouth, you don't care about safety not me. And for what it's worth I'm an electrical engineer first, so if you have some inferiority complex about software you don't have to apply it to me.

Hey, you're the one who said "faster is better", not me

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

#228

Post by jimminyx »

srinath693 wrote: post #222

The "skills not features" contribution model is the most interesting part of this. Instead of a project that grows into another 52-module beast, contributors teach Claude how to transform the codebase per-user. It's basically contributing build instructions instead of build artifacts. If it actually works in practice, it's a genuinely novel approach to keeping small projects small.

Thanks! I believe that's where software is going. Just need Karpathy to give it a name so it can take off ;)

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

#229

Post by jimminyx »

river_otter wrote: post #178

Great idea and name the danger here which I'll be interested to track is how do you keep this "nano"? Since it's built for you, you'll continue adding features i assume which over time will make this not very nano. I guess I'm wondering if there could be some small design tweaks of the repo that make this usable as a long term "fork the base and make it your own" concept

I will keep the source code as a minimal implementation that has the core capabilities that made Clawdbot/OpenClaw useful: chat with it via messaging app (only one channel included out of the box), memory (minimal implementation that leverages CLAUDE.md and the filesystem), cron jobs, browser.

If I want to add additional capabilities for myself, I'll contribute them to the project as skills for claude code to modify the code base, rather than directly to the source. I actually want to reduce the size of the base implementation and have a PR open to strip out 300-400 LOC

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

#230

Post by esskay »

swordsith wrote: post #143
esskay wrote: post #132

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 ha…

> 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

Yeah it didnt cost anything as its free right now, this was literally a test to see what the hype was about. All I'd asked it to do was get its self set up to be a helpful marketing assistant for a web-based product. No specifics or anything, it just decided to be 'helpful'.
Post reply on HN