# espressif/esp-claw

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

Repository: https://github.com/espressif/esp-claw
Canonical: https://ross.abutalabs.com/products/esp-claw
Homepage: https://esp-claw.com/
Language: C
License: Apache-2.0
License Family: permissive
Last push: 2026-08-20T03:30:29+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 56, longevity 9
- inputs: {"age_days": 138, "days_push": 13, "days_rel": 82, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2051, forks 427 (observed 2026-08-28T04:06:09.178821+00:00)

## What it is
ESP-Claw is Espressif's 'Chat Coding' AI agent framework for IoT devices, reimplemented in C for ESP32-series chips. It lets users define device behavior through natural conversation, combining LLM decision-making with locally executed Lua rules, event-driven sensing, MCP client/server support, and on-chip long-term memory.

## Use cases
- build an AI agent on an ESP32 that senses and acts locally
- define IoT device behavior by chatting instead of writing code
- run an MCP server/client on an embedded microcontroller
- create millisecond-latency event-driven automations on cheap hardware
- store user preferences and habits on-device without cloud dependency
- turn an ESP32 into an autonomous decision-making edge device

## When to choose
- you want LLM-driven agent behavior running directly on ESP32 hardware
- you need offline-capable, event-driven device logic with millisecond response
- you want non-programmers to configure devices via chat messages
- you need MCP integration to expose hardware capabilities to agents

## When to avoid
- your project targets non-Espressif microcontrollers
- you need a general-purpose cloud-hosted agent framework
- you require heavy LLM inference that exceeds MCU resources

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, mcp, llm-inference, iot, embedded, chatbot
- domain: artificial-intelligence, iot, embedded-systems
- platform: embedded, iot, c
- tags: esp32, espressif, edge-ai, chat-coding, lua, event-driven, on-device-memory, edge-agent, ai-agents, automation

## Member repositories
- espressif/esp-claw (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:09.178821+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:57:31.014632+00:00, confidence not recorded.
  - readme: https://github.com/espressif/esp-claw (fetched 2026-08-28T04:06:09.178821+00:00, sha c9550af7c71f)
  - homepage: https://esp-claw.com/ (fetched 2026-08-29T10:37:42.703136+00:00, sha 391937235cbe)
- Data as of 2026-08-30T08:39:29.467469+00:00.