espressif/esp-claw

ESP-Claw, a "Chat Coding" AI agent framework for IoT devices

What it solves

ESP-Claw transforms traditional IoT devices from passive executors of commands into active decision-making centers. It allows users to define device behavior through natural language conversations (Chat Coding) instead of traditional programming, enabling the device to handle sensing, decision-making, and execution locally on low-cost ESP32-series chips.

How it works

The framework implements an Agent Runtime on the device. It uses an event-driven architecture where any event can trigger an "Agent Loop" for rapid response. To enable dynamic behavior changes without flashing new firmware, it utilizes dynamic Lua loading. It also supports structured memory to keep privacy-sensitive data off the cloud and integrates with the Model Context Protocol (MCP) to act as both a server and client for other devices.

Who it’s for

IoT developers and hobbyists using Espressif ESP32-series chips (such as S3, P4, C5) who want to build intelligent, agentic edge devices that can be programmed via chat interfaces.

Highlights

  • Chat as Creation: Define device logic via IM chat (Telegram, QQ, Feishu, WeChat) using LLMs (OpenAI, Anthropic, DeepSeek, Qwen).
  • Edge Agent Runtime: Local execution of the sensing-decision-execution loop on inexpensive hardware.
  • Event-Driven: Millisecond-level response times for triggered events.
  • MCP Support: Standardized communication with other MCP-compatible devices.
  • Browser-Based Flashing: One-click online flashing for supported boards without needing a local development environment.

Related

  • Project
    78/xiaozhi-esp32

    An open-source ESP32-based AI voice chatbot framework that integrates LLMs and the Model Context Protocol (MCP) for real-time voice interaction and hardware control.

  • Project
    akdeb/ElatoAI

    A framework for deploying real-time voice AI models on ESP32 devices, enabling low-latency speech-to-speech interactions via edge functions.

  • Project
    espressif/esp-sr

    ESP‑SR is Espressif’s on‑device speech‑recognition framework for ESP32 MCUs. It bundles a tiny audio front‑end, wake‑word detection (WakeNet), voice‑activity detection (VADNet), offline command spotting (MultiNet), and speech synthesis, all optimized for low‑memory, low‑power chips. The library is modular, supports multiple languages, and lets developers add voice control to IoT devices without needing cloud services.

  • Project
    erthorpabar/pabar_agent_runtime

    An AI agent runtime framework that integrates chat, RAG, and agentic loops to enable professional automation tasks across desktop and mobile platforms.

  • Project
    xinnan-tech/xiaozhi-esp32-server

    A backend server for the xiaozhi-esp32 project that enables ESP32 devices to become AI assistants with voice, vision, and smart home control capabilities.