memovai/mimiclaw

Registry

Summary

MimiClaw is a lightweight, open-source implementation of OpenClaw designed to run on ultra-low-cost hardware (as low as a $5 chip) without an operating system, Node.js, or a Raspberry Pi. It provides a hardware-native agent OS for edge AI agents, prioritizing local storage, shareability, and privacy.

Key features

• Runs on a $5 chip without OS, Node.js, or Raspberry Pi
• Hardware-native agent OS for edge AI agents
• Local-first storage with shareability and privacy
• Open-source implementation of OpenClaw
• Designed for ultra-low-cost, low-power deployment

Use cases

• Running AI agents on low-cost edge devices
• Privacy-focused local AI assistant deployment
• Embedded systems with agent-based automation
• Education and prototyping for hardware AI agents
• IoT devices requiring on-device intelligence

README excerpt

# MimiClaw: Pocket AI Assistant on a $5 Chip <p align="center"> <img src="assets/banner.png" alt="MimiClaw" width="500" /> </p> <p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a> <a href="https://deepwiki.com/memovai/mimiclaw"><img src="https://img.shields.io/badge/DeepWiki-mimiclaw-blue.svg" alt="DeepWiki"></a> <a href="https://discord.gg/r8ZxSvB8Yr"><img src="https://img.shields.io/badge/Discord-mimiclaw-5865F2?logo=discord&logoColor=white" alt="Discord"></a> <a href="https://x.com/ssslvky"><img src="https://img.shields.io/badge/X-@ssslvky-black?logo=x" alt="X"></a> </p> <p align="center"> <strong><a href="README.md">English</a> | <a href="README_CN.md">中文</a> | <a href="README_JA.md">日本語</a></strong> </p> **The world's first AI assistant(OpenClaw) on a $5 chip. No Linux. No Node.js. Just pure C** MimiClaw turns a tiny ESP32-S3 board into a personal AI assistant. Plug it into USB power, connect to WiFi, and talk to it through Telegram — it handles any task you throw at it and evolves over time with local memory — all on a chip the size of a thumb. ## Meet MimiClaw - **Tiny** — No Linux, no Node.js, no bloat — just pure C - **Handy** — Message it from Telegram, it handles the rest - **Loyal** — Learns from memory, remembers across reboots - **Energetic** — USB power, 0.5 W, runs 24/7 - **Lovable** — One ESP32-S3 board, $5, nothing else ## How It Works  You send a message on Telegram. The ESP32-S3 picks it up over WiFi, feeds it into an agent loop — the LLM thinks, calls tools, reads memory — and sends the reply back. Supports both **Anthropic (Claude)** and **OpenAI (GPT)** as providers, switchable at runtime. Everything runs on a single $5 chip with a

Topics