NanoClaw
AI
personal ai agent
SHOW HN2026
How HN took it
10 positive, 22 neutral or asking, 1 mixed, 35 critical, out of 68 comments about the project. Thread score -0.33.
Docs: 0 for, 14 againstIdea: 5 for, 5 againstPrivacy: 2 for, 7 againstExecution: 0 for, 5 againstPricing: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Smaller, more understandable alternative to OpenClaw
From 2 comments
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,…
mark_l_watson on HNOP 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…
jimminyx on HN
Apple container isolation is a good idea
From 2 comments
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.…
thepoet on HNi installed clawdbot twice but didn't really use it because i couldn't wrap my head around the skills and plugins, this looks so much more managable. and +1 for apple containers
ccheshirecat on HN
Skills-not-features contribution model is novel
From 1 comment
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…
srinath693 on HN
Objections
README and docs look LLM-written and contained hallucinations such as a nonexistent repo
From 2 comments
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…
hebejebelus on HN``` 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…
avaer on HN
Possible violation of Claude Code terms of service
From 1 comment
This violates the Claude Code subscription terms of service, so please be careful. This project violates Claude Code's Terms of Service by automating Claude to create an…
pulkas on HN
Security risk of an agent with access to shared chats and prompt injection
From 2 comments
> 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…
popcorncowboy on HNOP 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…
jimminyx on HN
Sandbox does not prevent outbound actions the agent needs
From 1 comment
Not seeing how the sandbox prevents anything really. The point of OpenClaw is to connect out to different systems.
ramoz on HN
Requests
Get the Agent SDK to use the host's authenticated session inside containers
From 1 comment
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…
jimminyx on HN
Make it agent agnostic rather than tied to Claude Agent SDK
From 1 comment
def appreciate this more compact approach; everything is an experiment rn. I realize you used Claude Agent SDK on purpose but I'd really like to this to be agent agnostic. Maybe…
elgrantomate on HN
Support MCP tools
From 1 comment
Can you use MCP tools? I saw that with open claw they moved away from that which I personally didn't like but
Johnny_Bonk on HN
Questions
Is the 500 line count accurate
From 3 comments
Where are those 500 lines of code?
ivanstepanovftw on HN500 lines? Single files in that repo already have more than 500 lines.
moi2388 on HNI 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,…
mark_l_watson on HN
How is the agent sandboxed from external actions
From 2 comments
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.…
thepoet on HNNot seeing how the sandbox prevents anything really. The point of OpenClaw is to connect out to different systems.
ramoz on HN
How does it differ from running Claude Code with skip permissions in a container
From 1 comment
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…
reassess_blind on HN
Whether the Baileys WhatsApp library risks Meta bans
From 1 comment
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/
aitchnyu on HN
Alternatives named
Claude Code with skip-permissions in a container
From 1 comment
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…
reassess_blind on HN
coderunner sandbox
From 1 comment
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.…
thepoet on HN