PicoClaw ultra-lightweight personal AI Assistant runs on just 10MB of RAM

3 min read Original article ↗

PicoClaw is an ultra-lightweight personal AI Assistant designed to work on less than 10 MB RAM and suitable for resource-constrained embedded boards such as the Sipeed LicheeRV Nano SBC going for around $15 and powered by a SOPHGO SG2002 RISC-V SoC with 256MB on-chip DDR3.

I keep reading news about the OpenClaw personal AI assistant, after first finding out about it when the Cubie A7S SBC was launched. OpenClaw (previously ClawdBot) clears your inbox, sends emails, manages your calendar, and checks you in for flights from WhatsApp, Telegram, or any chat app. It’s been shown to run a range of hardware platforms, but it can be resource-intensive, and HKUDS created the nanobot ultra-lightweight personal AI assistant with about ~4,000 lines of Python code, or roughly 99% smaller than Clawdbot’s 430k+ lines. PicoClaw further builds on the nanobot project, and has been “refactored from the ground up in Go through a self-bootstrapping process, where the AI agent itself drove the entire architectural migration and code optimization”.

PicoClaw lightweight personal AI Assistant embedded systems

PicoClaw highlights:

  • Lightweight: <10MB Memory footprint, 99% smaller than OpenClaw
  • Suitable for $10 hardware (98% cheaper than a Mac mini)
  • 400x Faster startup time, boots in 1 second on a 600 MHz core.
  • Portability – Single self-contained binary across RISC-V, ARM, and x86
  • AI-Bootstrapped – Written in Go with 95% agent-generated core with human-in-the-loop refinement

The comparison table below, provided by Sipeed, shows the difference between OpenClaw, Nanobot, and PicoClaw.

OpenClawNanoBotPicoClaw
LanguageTypeScriptPythonGo
RAM>1GB>100MB< 10MB
Startup time (on 800 MHz core)
>500s>30s<1s
CostMac Mini ($599)Most Linux SBC (~$50)Any Linux Board (~$10+)

You can install it by downloading the binary for RISCV64 Linux, ARM64 Linux, AMD64 Linux, or AMD64 Windows, or build it from source:

git clone https://github.com/sipeed/picoclaw.git

cd picoclaw

make deps

make build # Build, no need to install

make build-all # Build for multiple platforms

make install # Build And Install


You’ll then need to set your API key(s) for your select LLM provider and optional Brave Search in ~/.picoclaw/config.json, and start it with something like:

picoclaw agent -m "What is 2+2?"


The next step is to configure the Telegram or Discord chat app. Check out the full instructions and code on GitHub. I assume it might also work on some OpenWrt routers.

Picoclaw AI Assistant Workflows

Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress. We also use affiliate links in articles to earn commissions if you make a purchase after clicking on those links.