AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction
2026-06-22 • Artificial Intelligence
Artificial IntelligenceOperating Systems
AI summaryⓘ
The authors created AOHP, a modified version of Android designed specifically to work better with AI agents, which are programs that can perform tasks automatically across different apps. Normal operating systems focus on running apps but don't support these AI agents well, causing inefficiencies and safety issues. AOHP treats AI agents as important parts of the system, adding new features to help agents work more smoothly and securely. Tests showed that AOHP helped agents complete tasks more successfully, reduced the computing cost, and improved compliance with security rules.
AI agentsoperating systemAndroid Open Source Projectagent-native OSservice compositionruntime environmentinformation flow securitytask completionexecution costuser interface
Authors
Shanhui Zhao, Jiacheng Liu, Guohong Liu, Jichao Yan, Jialei Ye, Yuhao Yang, Hao Wen, Shizuo Tian, Yizhen Yuan, Yuxuan Chen, Yunxin Liu, Ju Ren, Ya-Qin Zhang, Chao Huang, Yao Guo, Yuanchun Li
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.