AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction

2026-06-22

AI Summary

Existing operating systems lack native support for AI agents, resulting in high overhead and security vulnerabilities that hinder their widespread adoption. This work presents the first framework built upon AOSP that treats AI agents as first-class operating system entities, introducing three core mechanisms: personalized service orchestration, lightweight agent interfaces, and mandatory secure information flow control. Experimental evaluation demonstrates that the proposed system improves task completion rates by 21.12% and reduces token consumption by 51.55% on representative workloads, while rigorously enforcing security and compliance requirements. By providing an open-source platform and foundational techniques, this study advances the research and development of agent-native operating systems.

Abstract

AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, manage memory, and complete tasks that span applications and data sources. Most existing end-user operating systems, however, are designed for application-centric workflows and offer little native support for AI agents. This mismatch limits the wider adoption of agents and leads to execution overhead and safety risks when running agents on conventional systems. While the concept of agent-native operating systems is emerging, the research community lacks an open testbed to explore the architectural primitives desired for agent-mediated interaction. We present AOHP (Android Open Harness Project), an OS-level agent harness built on the Android Open Source Project (AOSP). The core design principle of AOHP is to treat agents as first-class OS actors, enabling adaptive user interfaces and agent-friendly runtime environments. AOHP preserves the mature Android software and hardware ecosystem while introducing three agent-oriented system mechanisms: personalized service composition, efficient agent interfaces, and secure information flow. Based on preliminary experiments on challenging tasks covering key capabilities of OS agents, AOHP shows clear advantages in task completion (+21.12% completion rate), execution cost (-51.55% token cost), and security-policy compliance.

Problem

• AI agents
• operating systems
• agent-native OS
• system support
• execution overhead

Innovation

• agent-native OS
• personalized service composition
• efficient agent interfaces
• secure information flow
• OS-level agent harness