OpenAgenet, abbreviated as OAN, is an open infrastructure project for trustedAgent interconnection. It addresses a problem that becomes visible when Agentsmove from isolated applications into open, multi-operator networks: before anAgent can safely discover, select, and invoke another Agent, it needs a way toverify identity provenance, governance state, discovery authorization, freshness, and pre-connection trust evidence. OAN is designed as aprotocol-neutral trust layer. It does not replace Agent interaction protocols, tool protocols, model orchestration frameworks, or application-level workflows. Instead, it provides did: oan-based resource identity, governance-backed admission, Registrar-assisted onboarding, Root-verifiedpackage publication, authorization-aware Discovery, Root-issued infrastructureauthorization VCs, and signed trusted invocation. The architectural center ofOAN is the combination of federated governance, resource identity, and trustedDiscovery, rather than a single directory or naming service. This white paperexplains the motivation, architecture, roles, governance model, relationshipwith MCP, A2A, and ANP, deployment patterns, cooperation model, on-chaingovernance layer, prototype status, performance profile, and roadmap of OAN.
XU JINLIANG (Sun,) studied this question.