← Back to LLM Wiki
LLM Wiki · Agent Runtime · Claw Ecosystem

PicoClaw

The ultra-lightweight IoT runtime in the Claw ecosystem. Go, under 10MB RAM, built with Sipeed to run on $10 RISC-V boards, IP cameras, routers, and microcontrollers.
PicoClaw answers the question nobody else was asking: what if the agent lives on the sensor, not the server? The runtime targets hardware where Llama, Qwen, and even Phi can't load — single-board computers, embedded Linux devices, IP cameras, industrial PLCs. The inference runs elsewhere (edge server, cloud); PicoClaw handles the agent protocol, tool dispatch, and local state in <10MB of RAM.
Agent Runtime Go IoT <10MB RAM RISC-V

Quick Facts

Category
Agent runtime (not a model)
Language
Go
Memory footprint
Under 10MB RAM at runtime
Partner
Sipeed (RISC-V hardware maker)
Target hardware
$10 RISC-V SBCs · IP cameras · routers · microcontrollers · embedded Linux
Architecture
Agent-on-device; inference off-device via MQTT / gRPC
Inference
Offloaded to edge server (OpenClaw host) or cloud endpoint
License
Open source (see Claw ecosystem on GitHub)

Summary

PicoClaw is the IoT and embedded member of the Claw family. It was developed in partnership with Sipeed, the Shenzhen-based company behind the sub-$10 RISC-V boards (LicheePi, MaixCube) that have made real embedded Linux cheap enough for one-per-sensor deployments. The technical constraint — under 10MB RAM at runtime — rules out running an LLM locally. PicoClaw's architectural premise is that the agent protocol can live on the device while the inference lives elsewhere.

The on-device runtime handles: receiving events (MQTT, serial, GPIO), dispatching tool calls (local GPIO writes, sensor reads, actuator control), maintaining a minimal state machine, and forwarding LLM calls via MQTT or gRPC to an OpenClaw or ExoClaw host. The agent looks the same from the control plane's perspective; the inference just happens a network hop away.

Architecture

When to Choose PicoClaw

PicoClaw is the right runtime when the agent's environment is the physical world and the hardware envelope is small: smart cameras with agentic triggers, industrial sensor fleets, retail IoT, home automation, agricultural deployments. Any scenario where one agent per device times tens-to-thousands of devices makes more sense than a few centralized agents polling.

Tradeoffs

Related

References

  1. Organized AI on GitHub
  2. Sipeed — RISC-V hardware partner
  3. Edge Compute Economics — Organized AI