HearthNet: Edge Multi-Agent Orchestration for Smart Homes

TL;DR

HearthNet is an edge multi-agent orchestration system for smart homes that uses persistent, role-specialized LLM agents to manage devices through event-driven coordination, externalized context, and separation of concerns.

Contribution

The paper introduces HearthNet, a novel edge multi-agent system that externalizes context and separates planning, verification, and actuation for resilient smart-home control.

Findings

Prototype runs on commodity hardware and Android devices.

Demonstrates intent-driven multi-agent coordination from natural language.

Handles conflict resolution and rejects stale commands effectively.

Abstract

Smart-home users increasingly want to control their homes in natural language rather than assemble rules, dashboards, and API integrations by hand. At the same time, real deployments are brittle: devices fail, integrations break, and recoveries often require manual intervention. Existing agent toolkits are effective for session-scoped delegation, but smart-home control operates under a different scenario: it is persistent, event-driven, failure-prone, and tied to physical devices with no shared context window. We present HearthNet, an edge multi-agent orchestration system for smart homes. HearthNet deploys a small set of persistent, role-specialized LLM agents at the home hub, where they coordinate through MQTT, Git-backed shared state, and root-issued actuation leases to govern heterogeneous devices through thin adapters. This design externalizes context, preserves execution history, and separates planning, verification, authorization, and actuation across explicit boundaries. Our current prototype runs on commodity edge hardware and Android devices; it keeps orchestration, state management, and device control on-premise while using hosted LLM APIs for inference. We demonstrate the system through three live scenarios: intent-driven multi-agent coordination from ambiguous natural language, conflict resolution with timeline-based tracing, and rejection of stale or unauthorized commands before device actuation.