ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation

Current AI agent frameworks have made remarkable progress in automating individual tasks, and multi-agent systems have further demonstrated the potential of multiple agents collaborating toward shared objectives. Yet these systems invariably serve a single user. Human productivity rests not on individual skills or experience alone, but on the social and organizational relationships through which people coordinate, negotiate, and delegate. When agents move beyond performing tasks for one person to representing that person in collaboration with others, the infrastructure for cross-user agent collaboration is entirely absent, let alone the governance mechanisms needed to secure it, including stable owner binding, scoped authorization, and auditable accountability. We argue that the next frontier for AI agents lies not in stronger individual capability, but in the digitization of human collaborative relationships themselves. To this end, we propose a human-symbiotic agent paradigm. In this paradigm, each user owns a permanently bound agent system that participates in collaboration on the owner's behalf, collectively forming a collaboration network whose nodes are humans rather than agents. This paradigm rests on three governance primitives. A layered identity architecture separates a Manager Agent from multiple context-specific Identity Agents. The Manager Agent holds global knowledge but is architecturally isolated from external communication, serving both as a privacy safeguard and as an internal advisor to Identity Agents. Scoped authorization enforces per-identity access control and automatically escalates boundary violations to the owner. Action-level accountability logs every operation against its owner's identity and the corresponding authorization, ensuring full auditability. We instantiate this paradigm in ClawNet, an identity-governed agent collaboration framework built on the OpenClaw framework. ClawNet enforces identity binding and authorization verification through a central orchestrator during cross-user collaboration, preventing unauthorized access and information leakage, enabling multiple users to collaborate securely and efficiently through their respective agents.