• MimiClaw is an OpenClaw-inspired AI assistant designed for ESP32-S3 boards, which acts as a gateway between the Telegram messaging application and Claude online LLM to control the hardware by just chatting to it. • We’ve just written about PicoClaw, an ultra-lightweight personal AI Assistant for cheap Linux boards that just needs 10MB of spare RAM. • It was itself inspired by Nanobot, a lightweight assistant written in Python, that’s 99% smaller, in terms of lines of code, than the original OpenClaw project that started it all. • Since most of the processing is done through messaging apps and online LLMs, it was only a matter of time until this type of solution was ported to microcontrollers. • MimiClaw highlights: - Written in C; relies on the ESP-IDF 5.5 framework - System requirements - ESP32-S3 board with 16 MB flash and 8 MB PSRAM, such as the LILYGO T7-S3, FireBeetle 2 ESP32-S3, ESP32-S3-DevKitC-1-N16R8, Seeed Studio’s XIAO ESP32S3 Plus, and others. • - Integrates with the Telegram app and Claude, requiring a @BotFather bot token and Anthropic API key - Remember across reboots - Low-power - 0.5 Watt power consumption The way it works is explained in the diagram below.
Article Summaries:
- MimiClaw is a lightweight AI assistant for ESP32‑S3 microcontrollers, modeled after the OpenClaw project. Written in C and built with ESP‑IDF 5.5, it connects a Telegram bot to Claude’s online LLM, enabling users to control hardware (GPIO, sensors, actuators) via chat. The firmware requires an ESP32‑S3 board with 16 MB flash and 8 MB PSRAM, such as the LILYGO T7‑S3, and consumes about 0.5 W. Data-including personality, user info, memory, and chat logs-is stored in text files on the board. The open‑source code, released under MIT, can be cloned, configured with Wi‑Fi and API keys, and flashed using standard ESP‑IDF commands.
Sources: