Zclaw – The 888 KiB Assistant
zclaw.dev

・

69 points

・

kristianpaul

・

3 days ago

39 comments

tehsauce ・ 5 hours ago

“888 KiB Assistant” but the assistant itself is a multi terabyte rental-only model stored in some mysterious data center.

  • amelius ・ 5 hours ago

    I'm getting "serverless" flashbacks.

  • kristianpaul ・ 4 hours ago

    My model is at home... just 16Gb still a lot but just FYI

  • Rebelgecko ・ 4 hours ago

    It seems to support connecting to your own LLM on the same LAN

    • croes ・ 2 hours ago

      The point is the agent is still the LLM. No LLM, no agent.

    • dheera ・ 2 hours ago

      I tried connecting OpenClaw to ollama with a V100 running qwen3.5:35b but it was really, really, really slow (despite ollama itself feeling fairly fast).

      These "claw" agents really multiply the tokens used by an obscenely huge factor for the same request.

0xbadcafebee ・ 3 hours ago

For people who don't get this: it's a Home Assistant type thing. You don't do inference on it, you send it a message on Telegram and it does things with physical things through GPIO. You could use a $140 Raspberry Pi with 8GB RAM and host a local model on it plugged into 30W AC power... or you could use a $10 ESP32 which can run for weeks on a tiny battery, and your existing Wifi connection with a cheap cloud model (cloud models are as cheap as $0.02/1MTokens). This makes it easier to ramp up on new ESP32 projects. You can just tell it to do things / give you info, rather than having to write code.

  • newswasboring ・ 34 minutes ago

    The model can be taken care of in cloud but hardware also depends upon what we want to do right? If we want to run some lightweight python scripts etc, we cant use ESP32 right?

amelius ・ 5 hours ago

Me: "GPIO 5 can be active for a maximum of 100ms, then it needs to cool down for at least 1s. Otherwise the MOSFET is fried."

Zclaw: "GPIO 5 is active now, however the server is not responding so I'm awaiting further instructions."

gas9S9zw3P9c ・ 5 hours ago

I fail to understand why 888 KiB matters if it's just a wrapper around a cloud api.

  • ramon156 ・ 5 hours ago

    Have you seen OpenClaw's codebase? 680.000 LOC.

    I care how big it is.

  • Rebelgecko ・ 4 hours ago

    A lot of the *claws emphasize binary size and lines of code. I think for better or worse people treat codebase size as a proxy for "how much of the project is unsupervised, unmaintainable, buggy AI slop?"

  • boznz ・ an hour ago

    8 is lucky number in China

  • mihaelm ・ 5 hours ago

    Because of resource-constrained environments, the primary deployment target seem to be microcontrollers. You can get ESP32 boards for pretty cheap.

  • renewiltord ・ 5 hours ago

    Because it means you can run it on an ESP32 which is a low power microprocessor package.

Retr0id ・ 3 hours ago

888KiB is quite large, but I see they're including the whole rest of the firmware in that number, fair enough. Their actual application code weighs only 35,742 bytes, compiled.

hidelooktropic ・ 5 hours ago

There are many concerns and areas for improvement with open claw and other similar projects (continuous loop script with broad OS access that manages your agents and interfaces with a standard messaging app)

However, file size I have never seen on that list. I would rather offer for something that is even bigger in file size so it afford certain functionality like better security tighter permissions however it would do that.

  • stavros ・ 4 hours ago

    I made a secure one:

    https://github.com/skorokithakis/stavrobot

    Everything runs in containers (I run it on a server along with everything else), plugins have a permission system so eg the AI can read emails but not delete or send, etc.

    I really like it, I run it as my main agent and it has been extremely helpful.

    • croes ・ 2 hours ago

      Part of the usefulness is based on the same thing that makes it so dangerous.

      If it can only read but not act, it’s safer but less useful.

      • stavros ・ 2 hours ago

        I can't restrict OpenClaw if I don't need the extra capabilities. I can restrict this.

  • mihaelm ・ 4 hours ago

    File size is a legit property to keep in mind if your goal is to create an agent that runs on ESP32 boards. They don't expect you to run Zclaw on Mac Mini.

    • allthetime ・ 4 hours ago

      What's the use case for running this on a tiny board? Isn't the whole point that it can use your computer for you?

      • mihaelm ・ 4 hours ago

        For something like OpenClaw yes, but not for Zclaw. I think the naming is more about riding the current wave of Claw-related interest rather than positioning it as competition or replacement for other clawies.

        Zclaw is about running an agent in your embedded system.

      • markstos ・ 4 hours ago
        ・ 3 more

        The examples seem to suggest it would be chatting with your home automation in natural language.

        • fc417fc802 ・ 3 hours ago
          ・ 2 more

          Before you know it your smart thermostat will be blogging. The joke is on everyone who thought IoT couldn't get any worse. Just imagine the new landscape of security vulnerabilities this opens up.

          • markstos ・ 3 hours ago

            My "smart" gas stove can be turned on over the internet (if I allow it to connect)—perfect appliance to put an LLM in charge of.

jesse_dot_id ・ 5 hours ago

Clicked on this expecting to see a crontab file.

wartywhoa23 ・ 3 hours ago

Still lightyears from a one-bit AI assistant. Send 1 to save the humankind, 0 to exterminate. And hurry up because it's in undefined state right now!

karolcodes ・ 5 hours ago

1. why

  • dpe82 ・ 4 hours ago

    2. fun

  • rvz ・ 4 hours ago

    2. hype