<img alt="ESP-Claw logo" src="https://github.com/espressif/esp-claw/raw/v0.1.0/docs/src/assets/logos/logo.svg" width="50%" />

ESP-Claw 🦞 AI Agent Framework for IoT Devices

💬 Chat as Creation · 🚀 Millisecond Response · 🧩 Smart and Extensible · 😋 Grows with You

<a href="https://www.espressif.com">
  <img src="https://img.shields.io/badge/runs_on-ESP32_Series-red?style=flat-square" alt="Runs on ESP32 Series" />
</a>
<a href="https://github.com/espressif/esp-claw/raw/v0.1.0/LICENSE">
  <img src="https://img.shields.io/github/license/espressif/esp-claw?style=flat-square" alt="License" />
</a>

Home | Docs | Online Flashing | Build from Source | 简体中文

ESP-Claw is Espressif's Chat Coding AI agent framework for IoT devices. It defines device behavior through conversation and completes the full loop of sensing, decision-making, and execution locally on Espressif chips. Inspired by the OpenClaw concept and reimplemented in C, ESP-Claw is lightweight, intelligent, and continuously evolving. With just an ESP32-series chip that costs only a few dollars, you can experience what makes ESP-Claw so nimble.

🌟 Key Features

Traditional IoT usually stops at connectivity: devices can connect to the network, but they cannot think; they can execute commands, but they cannot make decisions. ESP-Claw brings the Agent Runtime down onto Espressif chips, turning them from passive executors into active decision-making centers.

📦 Quick Start

ESP-Claw now supports a wide range of development boards based on ESP32-S3, ESP32-P4, ESP32-C5, and ESP32-S31, including breadboards, M5Stack CoreS3, and many others. Supported boards in ./application/edge_agent/boards/ can be flashed online directly: configuration and flashing are done entirely in the browser, with no need to compile firmware locally or install a development environment first.

You can also build ESP-Claw locally. Please refer to the local build documentation for board adaptation, building, and flashing. Boards not listed above, as well as chips like the ESP32-P4, can also be supported through local builds and flashing.

You can find practical examples in our documentation.

Supported Platforms

<img alt="Supported Platforms" src="https://github.com/espressif/esp-claw/raw/v0.1.0/docs/static/claw-providers-black.webp" width="90%" />

LLM: ESP-Claw now supports both OpenAI-style APIs and Anthropic-style APIs. It natively supports GPT models from OpenAI, Qwen models from Alibaba Cloud Bailian, Claude models from Anthropic, DeepSeek models from DeepSeek API, and also supports custom endpoints.

[!TIP]

ESP-Claw's self-programming capability depends on models with strong tool use and instruction-following ability. We recommend gpt-5.4, qwen3.6-plus, claude4.6-sonnet, deepseek-v4-pro or models with comparable capability.

IM: ESP-Claw supports Telegram, QQ, Feishu, and WeChat, and can be extended further.

Development Plan

ESP-Claw is still under active development. Feel free to open an issue to report problems or request features. You can also share your ideas through our online survey (in Chinese).

Click here to view our TODO List (in Chinese) and vote for the features or issues you care about. That helps us prioritize them sooner.

📷 Follow Us

If this project helps you, please consider giving it a star. ⭐⭐⭐⭐⭐

Star History

<img alt="Star History Chart" src="https://api.star-history.com/chart?repos=espressif/esp-claw&type=date&legend=top-left" />

Acknowledgements

Inspired by OpenClaw.

The implementation of Agent Loop, IM communication, and related capabilities on ESP32 also draws on MimiClaw.