TopoClaw: A Human-Centric and Topology-Aware Agent Operating System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Heyuan, Guan, Yeyi, Wang, Jihong, Wang, Mingzhi, Zhou, Jiamu, Qu, Xiangmou, Yin, Jiaxin, Liao, Xin, Lou, Xingyu, Wang, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918503103070208
author Huang, Heyuan
Guan, Yeyi
Wang, Jihong
Wang, Mingzhi
Zhou, Jiamu
Qu, Xiangmou
Yin, Jiaxin
Liao, Xin
Lou, Xingyu
Wang, Jun
author_facet Huang, Heyuan
Guan, Yeyi
Wang, Jihong
Wang, Mingzhi
Zhou, Jiamu
Qu, Xiangmou
Yin, Jiaxin
Liao, Xin
Lou, Xingyu
Wang, Jun
contents Large language models (LLMs) have evolved AI assistants into autonomous reasoning engines that maintain context, invoke tools, and pursue long-horizon tasks. This has spurred Agent Operating Systems (Agent OS) as kernel-like layers for lifecycle management, memory, scheduling, and access control. Yet most designs remain agent-centric, treating the OS as a single-host runtime for internal reasoning and tool use, leaving open how autonomous actions integrate with distributed, collaborative, permission-sensitive workflows. TopoClaw is an open-source, human-centric, topology-aware Agent OS modeling the user's ecosystem as two coupled structures: a physical device topology of heterogeneous surfaces and a social relationship topology of shared spaces, teams, and delegated roles. It unifies device operation, messaging, and skills around accountable cross-boundary execution, with three core contributions: (1) cross-device action placement, decoupling intent from actuation and routing distributed actions across the device cluster based on hardware affordances and user context; (2) cross-user identity attribution, treating agents as socially situated "Digital Twins" that coordinate in multi-user spaces while preserving provenance, role-aware permissions, and human accountability; (3) cross-context authority governance, pairing broad capability with distributed, context-aware policy enforcement across physical and social trust boundaries to bound proactive autonomy at the OS layer. This report presents TopoClaw as an engineering-oriented reference architecture, covering its design principles, runtime, cross-device execution, collaboration mechanisms, security model, and deployment outlook.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15556
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TopoClaw: A Human-Centric and Topology-Aware Agent Operating System
Huang, Heyuan
Guan, Yeyi
Wang, Jihong
Wang, Mingzhi
Zhou, Jiamu
Qu, Xiangmou
Yin, Jiaxin
Liao, Xin
Lou, Xingyu
Wang, Jun
Human-Computer Interaction
Large language models (LLMs) have evolved AI assistants into autonomous reasoning engines that maintain context, invoke tools, and pursue long-horizon tasks. This has spurred Agent Operating Systems (Agent OS) as kernel-like layers for lifecycle management, memory, scheduling, and access control. Yet most designs remain agent-centric, treating the OS as a single-host runtime for internal reasoning and tool use, leaving open how autonomous actions integrate with distributed, collaborative, permission-sensitive workflows. TopoClaw is an open-source, human-centric, topology-aware Agent OS modeling the user's ecosystem as two coupled structures: a physical device topology of heterogeneous surfaces and a social relationship topology of shared spaces, teams, and delegated roles. It unifies device operation, messaging, and skills around accountable cross-boundary execution, with three core contributions: (1) cross-device action placement, decoupling intent from actuation and routing distributed actions across the device cluster based on hardware affordances and user context; (2) cross-user identity attribution, treating agents as socially situated "Digital Twins" that coordinate in multi-user spaces while preserving provenance, role-aware permissions, and human accountability; (3) cross-context authority governance, pairing broad capability with distributed, context-aware policy enforcement across physical and social trust boundaries to bound proactive autonomy at the OS layer. This report presents TopoClaw as an engineering-oriented reference architecture, covering its design principles, runtime, cross-device execution, collaboration mechanisms, security model, and deployment outlook.
title TopoClaw: A Human-Centric and Topology-Aware Agent Operating System
topic Human-Computer Interaction
url https://arxiv.org/abs/2605.15556