Skip to content

Hello👋, welcome to ESP-Claw!

ESP-Claw

ESP-Claw is a Chat Coding AI agent framework for IoT devices. It defines device behavior through conversation and completes the full loop of sensing, reasoning, decision-making, and execution locally on Espressif chips.

Chat to Build

Define device behavior through IM chat + dynamic Lua loading, with generated logic persisted as local deterministic rules

Event-Driven

Devices report events proactively with millisecond-level response; if no rule matches, call LLM automatically with cloud-edge collaboration

Bi-Directional MCP

Devices act as both MCP Server and MCP Client, callable by external Agents while also calling external services proactively

Local Memory

Structured long-term memory with lightweight summary-tag retrieval, keeping privacy local

DimensionTraditional IoT (Cloud-Centric)ESP-Claw (Edge AI)
Processing logicPreset static rules (If-This-Then-That)LLM dynamic decision-making + Lua deterministic rules
Execution engineRule engineLLM + Lua + Router (three-tier event handling)
Control centerCloud serverEdge node (ESP chip)
Device protocolMQTT / Matter / proprietary SDKMCP as a unified language + multi-protocol bridging
Memory managementCloud data storageLocal structured memory (JSONL + tags)
Interaction modelApp / control panelIM chat (Telegram / WeChat / Feishu)
IntelligencePreset automationLLM + local rules (continuous evolution)

This tutorial walks you from zero to a working ESP32-S3 breadboard build, then flashes the latest ESP-Claw firmware.

ESP-Claw Breadboard

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.