Launched this week
NanoClaw
A lightweight alternative to OpenClaw, runs in containers.
97 followers
A lightweight alternative to OpenClaw, runs in containers.
97 followers
A lightweight alternative to OpenClaw that runs in containers for security. OpenClaw has 400,000 lines of code. NanoClaw does the same thing in 4000. NanoClaw is a personal Claude assistant that runs on WhatsApp and Telegram. It manages your email, researches the web, runs scheduled briefings, and coordinates agent swarms, all from your phone. The difference? Every agent runs inside an isolated Linux container. No ambient access. Secure by default
Hey Product Hunt! I'm Gavriel, creator of NanoClaw.
A couple months ago, my brother Lazer and I were running an AI agency and using Claude Code for everything. Operations, research, sales pipeline, client work. We set up an OpenClaw agent to manage our sales pipeline and it was doing the work of an employee. Honestly, maybe even better. I wanted to set up eight more across the company.
But I couldn't sleep at night. I looked under the hood and found nearly 400,000 lines of code, 70+ dependencies, and every agent running in the same process with shared memory. No real isolation. An agent in your family group chat had the same system access as one connected to your work repo. I wanted to give this thing the keys to our entire business, and there was nothing actually keeping it contained.
So I built NanoClaw over a weekend. The idea was simple: what if you got the same core functionality (WhatsApp messaging, persistent memory, scheduled tasks, web access) but every agent ran inside its own isolated Linux container? OS-level sandboxing, not application-level permission checks. And what if the entire codebase was small enough that you could actually read and audit it?
The whole thing is about 3,900 lines across 15 files. People tell me you can understand the full architecture in about eight minutes.
A few things I'm proud of:
→ Container isolation for every agent session (Apple Container on macOS, Docker on Linux)
→ Agent Swarms: teams of specialized agents that collaborate within your chat
→ A Skills system where the community extends NanoClaw by teaching Claude Code how to modify the codebase, instead of bloating the core with features
→ No config files. You talk to Claude Code and it customizes the software to your exact needs. Every fork is bespoke.
The project has grown to 18,000 GitHub stars and has been covered by The Register, VentureBeat, The New Stack, and CNBC. But what really drives me is the community. Developers are forking NanoClaw and making it their own, adding Telegram, Signal, Discord, email. Exactly the way it was designed to work.
The vision is bigger than a personal assistant. I believe this kind of architecture (minimal, auditable, container-isolated) is how AI agents should run everywhere. It's the orchestration layer that nudges developers toward using solid, secure building blocks instead of reinventing the wheel. We're keeping it open source and building it into a foundation that people can build real products and businesses on top of.
Would love to hear what you think, answer any questions, and hear what you'd build with it. And if you've already been using NanoClaw, tell me about it. I genuinely want to know.
🔗 GitHub: github.com/qwibitai/nanoclaw
🌐 Site: nanoclaw.dev
Wilco
Can a non-technical person build their own skills, or is this still a developer tool?
@on Absolutely. I think good skills require good systems and design thinking but not necessarily very advanced technical abilities. If you are comfortable with claude code you've probably got everything you need to contribute a good skill.
I have set up Nanoclaw on a low-spec Digital Ocean Linux server. I have a handful of Telegram bots that manage my comms, emails, calendar, my event management business and now content management and marketing.
This is the lightest, most useful, and most extensible framework I've encountered in years, and it is built on security.
Nanoclaw is just the right framework at just the right time. The attack surface in the default configuration with TailScale is close to zero, and I now have a Security bot alerting me to upgrades and conducting security research. It has an IPC setup and a global option for the containers, or they can be left locked down depending on your needs. The skills option is perfect. Extensibility with minimal integration.
I am on the verge of letting the bots interact... 😱🤞
NanoClaw targets two very different audiences exceptionally well. The non-technical people. I sat next to a non-tech sales type who has mastered Excel. With me there to prevent del *.* , she got it up/running and was able to 'talk to it' and accomplish getting some tasks she wanted set up/automated. Safely, without any (and I mean any) tech knowledge beyond knowing how to type and ask questions. On here own, she had a tab open in her browswer asking, which is funny when you think about it, ChatGPT to help with how do I, using a prompt preface of "I am about as technical as a tuna sandwhich, keep it simple." She is a happy bunny and her iMac hums along nicely.
The second group are the propeller heads of which I proudly wear. Fork the repo, tear into it, custom this, custom that, get the PR, re-think this, that, etc. For grins? Ask Codex over in my VS Code instance to port the whole thing to Python, just because. All good, all works, and the code base is a rock solid us it as it or go wild bundle of joy.
This is, without question a textbook, prime case study of an Open Source solution done right. Outstanding efforts on the founder's part.
This is insane, been working with nano since early days and just love it - especially how it can modify its own code.
key question - any plans for making this work natively in a cloud environment - and still support WhatsApp as a channel?
Also - Does it support WhatsApp Business Official API instead of the unofficial baileys library?
Overcut
Very cool approach.
Running each agent in its own container with no ambient access is exactly how these systems should be built. As agents start managing real tools and data, security and isolation will matter a lot.
@yuval_hazaz I know, right? When the boundaries are clear everything's easier. This is exactly why we moved from processes to containers to begin with - it's the best abstraction we could find (at the time) for that isolation.
It's not perfect by any means - but I feel a whole lot different than when running process-based claws.
@yuval_hazaz Thanks, Yuval!
Hi all,
Lazer here. Gavriel created NanoClaw to serve our startup’s needs, and we’re its biggest users. NanoClaw manages our content pipeline, sales, and more!
Would love to hear how you use NanoClaw!