Amico: An Event-Driven Modular Framework for Persistent and Embedded Autonomy
This addresses the need for resilient, interactive autonomous agents in settings with limited compute and intermittent connectivity, though it appears incremental as it builds on existing modular and event-driven approaches.
The paper tackles the problem of existing autonomous agent frameworks struggling in real-world or resource-constrained environments by presenting Amico, a modular, event-driven framework optimized for embedded systems, which supports reactive, persistent agents across platforms like embedded devices and browsers via WebAssembly.
Recent advances in large language models (LLMs) and autonomous agents have enabled systems capable of performing complex tasks across domains such as human-computer interaction, planning, and web navigation. However, many existing frameworks struggle in real-world or resource-constrained environments due to their reliance on cloud-based computation, limited robustness in dynamic contexts, and lack of persistent autonomy and environmental awareness. We present Amico, a modular, event-driven framework for building autonomous agents optimized for embedded systems. Written in Rust for safety and performance, Amico supports reactive, persistent agents that operate efficiently across embedded platforms and browser environments via WebAssembly. It provides clean abstractions for event handling, state management, behavior execution, and integration with reasoning modules. Amico delivers a unified infrastructure for constructing resilient, interactive agents suitable for deployment in settings with limited compute and intermittent connectivity.