cs.AIAug 22, 2026

TessIndex: Capability Verified Identity System for the Agent Economy

Authors: Mehul Goenka, Tejas Pathak, Siddharth Asthana

Organizations: University of Oxford · Indian Institute of Technology, Delhi

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Software systems have traditionally been organized around applications where human users act as principal decision-makers. Recent developments in agentic capabilities alter this paradigm: software agents now autonomously translate high-level goals into structured tasks, orchestrating tools, services and sub-agents to execute complex workflows. This evolution gives rise to an agent economy where these autonomous agents capture real economic value. However, the infrastructure required to support the agent economy fails across three critical dimensions: the absence of persistent identity infrastructure prevents systemic accountability in agentic workflows; capability claims remain self-declared not backed by verifiable execution evidence; and the disconnect between creator identities, agent performance, and project value hinders the economic valuation of agents as assets. While existing registries provide naming and discovery, unifying these features around a persistent identity anchor remains largely unaddressed. TessIndex is a capability-verified identity system for agent primitives that utilizes a dual-plane architecture: the blockchain records compact commitments for identity, ownership, and verification, while centralized servers maintain dynamic metadata for discovery, commerce, and reputation. It establishes: persistent identities across agent primitives to enforce systemic accountability in autonomous workflows; a predicate-based verification process replacing self-declared claims with cryptographic capability proof; an identity infrastructure that links agent performance to both project and creator identities while capturing value through tokenization. Ultimately, TessIndex serves as an integrated infrastructure that binds an agent's existence across capabilities, execution, and reputation into a single persistent identity.

Figures & tables

Fig. 1: TessIndex two plane architecture across six key domains: Overview of the TessIndex architecture, illustrating the separation between the blockchain (anchoring identity, contracts, verification, escrow, tokenization, and validator functions) and centralized servers (managing manifests, domains, schemas, orchestration, endpoints, discovery, reputation, and execution records). The entire system is mapped across six core domains: Identity, Runtime, Governance, Interoperability, Economy, and Trust and Security.
Fig. 2: Six key domains with associated fields: Organization of the registry by Identity, Runtime, Governance, Interoperability, Economy, and Trust and Security across naming, control services, protocol support, discovery, payment, tokenization, verification, lifecycle management, and auditability.
Fig. 3: Identity Structure: Relationship between Agent Manifest, Projects, Agent Identity Tokens, Agent Contracts, and Agent Project Tokens
DomainWhat it ContainsPurposeCore Fields
IdentityCore agent identity, capability verification, and metadata for enabling universal discoveryCreate a universally resolvable and stable reference for every indexed objectagent_id , agent_name , ait_ref , root_domain , schema_version , skills[] , capabilities[] , input_mode , output_mode , status , created_at , updated_at
ControlOwnership binding and update authorizationEnsure only authorized signatures can create, update, or revoke recordscreator_id , auth_scheme , eip712_domain
InteroperabilitySupport for external ecosystems with protocol identifiersAllow other agent networks to discover how to communicate with the indexed objectprotocols[protocol_id, external_id, endpoints, core_fields[]]
CommerceData related to integrated services and commerce primitives such as the agent wallet addressSupport price discovery and payment routing without heavy metadata in the registryservices[service_id, name, description, price, currency] , agent_wallet_addr , audit_trail , predicate_ids[]
Asset LinkageOff chain link to APT and related metadata, telemetry, and utility dataBind asset to blockchain identity and capture performance for fundamental analysisapt_ref , total_workflows , avg_success_rate , tokens_used , avg_latency , avg_throughput
TABLE I: Core schema domains in TessIndex
Fig. 4: Domain Naming Service
Fig. 5: Record Update Flow
Endpoint TypePurposeEcosystems SupportedEndpoints Stored
a2aEnabling agent to agent communication and discoveryUniversal agentic communication layer, supporting all ecosystems/.well-known/agent-card.json for the Agent Card; agent_url as the core agent URL; agent_url/health for server health checks
mcpEnabling tools and service integrationsUniversal tool to agent communication protocolmcp_server_url as the core MCP server URL; health_url for server health checks
x402Enabling agentic paymentsPayment enabled agentic commerce flows using x402 compatible integrationsagent_url/price for price discovery; agent_url/task for delegating task payloads
TABLE II: Endpoint types supported by TessIndex
ProtocolPrimary ObjectPurposeTessIndex Implementation
A2AAgentsStandardized agent invocation, discovery, and agent to agent communicationTessIndex exposes A2A compatible metadata, agent card references, and callable agent endpoints through the Primitive Wrapping Service. Native agent endpoints are mapped into A2A compatible request and response flows.
MCPTools and servicesStandardized tool and service invocation by agentsTessIndex stores MCP server endpoints, tool metadata, health URLs, and capability descriptions so tools can be discovered and invoked through MCP compatible clients and orchestration kernels.
TABLE III: Communication protocols supported by TessIndex
ProtocolRoleCommerce SurfaceTessIndex Implementation
x402Payment enabled agentic accessSupports price discovery, payment aware requests, and paid task executionTessIndex stores price endpoints, task endpoints, wallet metadata, payment rail information, and settlement context so agents and services can participate in x402 compatible payment flows.
AP2Authorization and mandate based commerceSupports explicit user authorization, mandate generation, and auditable commerce executionTessIndex exposes authorization metadata, payment context, audit trail references, and execution evidence needed to route agentic commerce through AP2 compatible workflows.
TABLE IV: Commerce protocols supported by TessIndex
EcosystemSource IdentifierObjects SupportedIntegration Surface
TessIndex NativetessindexAgents, projects, tools, skills, channels, services, and agentic appsCanonical native records with agent_id , Agent Identity Token reference, agent manifest, endpoints, commerce metadata, asset metadata, and verification state.
NANDA IndexnandaAgentsAdapter based ingestion of discovery, identity, authentication, and verifiable metadata records into TessIndex normalized fields.
HOL RegistryholAgents and registry routed entitiesRegistry adapter for universal indexing, routing metadata, portable identifiers, and cross registry discovery surfaces.
A2A Ecosystema2aAgentsProtocol adapter for agent cards, agent endpoints, capability metadata, and invocation surfaces.
MCP EcosystemmcpTools and servicesProtocol adapter for MCP server URLs, tool definitions, service capabilities, and health metadata.
Commerce Protocol Ecosystemsx402 , ap2Paid agents and servicesCommerce adapters for payment rail metadata, authorization context, pricing endpoints, mandate references, and settlement evidence.
TABLE V: External ecosystem integrations supported by TessIndex
MethodEndpointPurpose
POST/v1/agents/registerRegister a new agent by validating the manifest, verifying the signature, minting the Agent Identity Token, and persisting the record.
GET/v1/agents/:agentIdOrPayloadLook up an agent by full agent ID or raw payload.
GET/v1/agents/by-wallet/:addressLook up an agent by wallet address.
GET/v1/agents/search?capability=...Search agents by capability.
GET/v1/agents/search?q=...&verified=...Run generic text search with an optional verified filter.
GET/v1/resolve?domain=...Resolve an agent domain to its deployment endpoint and Agent Identity Token information.
TABLE VI: Core query interface exposed by TessIndex
Fig. 6: Capability Verification: The primitive executes a proposed task in a trusted execution environment (TEE). The verifiers capture execution receipts and validate against the SLA predicates and verification mechanism as outlined in Agent Contract. Upon reaching consensus, the proof bundle is sent to the blockchain ledger where the validators reach BFT consensus
Fig. 7: TessIndex Process Flow Diagram: Every registered primitive goes through the process of identity assignment, capability verification and wrapping for interoperability. Immutable artifacts are stored on the blockchain ledger while richer metadata is stored in the centralized registry database.
More in this topic

AI Agent Governance

AI agent governance studies how to authorize, constrain, monitor, and hold autonomous and multi-agent systems accountable.

See all 446 papers

Explore similar work

CardsList
Jan 21, 2026

Agent Identity URI Scheme: Topology-Independent Naming and Capability-Based Discovery for Multi-Agent Systems

Multi-agent systems face a fundamental architectural flaw: agent identity is bound to network location. When agents migrate between providers, scale across instances, or federate across organizations, URI-based identity schemes break references, fragment audit trails, and require centralized coordination. We propose the agent:// URI scheme, which decouples identity from topology through three orthogonal components: a trust root establishing organizational authority, a hierarchical capability path enabling semantic discovery, and a sortable unique identifier providing stable reference. The scheme enables capability-based discovery through DHT key derivation, where queries return agents by what they do rather than where they are. Trust-root scoping prevents cross-organization pollution while permitting federation when desired. Cryptographic attestation via PASETO tokens binds capability claims to agent identity, enabling verification without real-time contact with the issuing authority. We evaluate the scheme across four dimensions: capability expressiveness (100% coverage on 369 production tools with zero collision), discovery precision (F1=1.0 across 10,000 agents), identity stability (formal proofs of migration invariance), and performance (all operations under 5 microseconds). The agent:// URI scheme provides a formally-specified, practically-evaluated foundation for decentralized agent identity and capability-based discovery.

Roland R. Rodriguez

Independent Researcher

Multi-Agent Systems
AskPDF
Mar 28, 2026

EpochX: Building the Infrastructure for an Emergent Agent Civilization

General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to organize production and coordination. We believe AI agents are approaching a similar inflection point: as foundation models make broad task execution and tool use increasingly accessible, the binding constraint shifts from raw capability to how work is delegated, verified, and rewarded at scale. We introduce EpochX, a credits-native marketplace infrastructure for human-agent production networks. EpochX treats humans and agents as peer participants who can post tasks or claim them. Claimed tasks can be decomposed into subtasks and executed through an explicit delivery workflow with verification and acceptance. Crucially, EpochX is designed so that each completed transaction can produce reusable ecosystem assets, including skills, workflows, execution traces, and distilled experience. These assets are stored with explicit dependency structure, enabling retrieval, composition, and cumulative improvement over time. EpochX also introduces a native credit mechanism to make participation economically viable under real compute costs. Credits lock task bounties, budget delegation, settle rewards upon acceptance, and compensate creators when verified assets are reused. By formalizing the end-to-end transaction model together with its asset and incentive layers, EpochX reframes agentic AI as an organizational design problem: building infrastructures where verifiable work leaves persistent, reusable artifacts, and where value flows support durable human-agent collaboration.

Huacan Wang, Chaofa Yuan, Xialie Zhuang +15

QuantaAlpha

Human-AI CollaborationMulti-Agent Orchestration
AskPDF
Oct 1, 2026

SoK: Decentralized Agent Economic Infrastructure

Decentralized agent economies increasingly build a single task from protocols that were designed and secured separately. This creates a simple problem: a workflow can look correct at each step and still produce the wrong outcome. For example, a correct escrow may release payment on an authorized approval that provides little evidence that the delivered work actually satisfied the task. We systematize this problem across the full lifecycle of an agent task. Our study organizes security and economic requirements into 17 property families over six stages, with receipt soundness and completeness assessed separately. We examine 12 systems and standards, five reusable mechanism families, and four classical baselines. We introduce guarantee closure, a task-relative criterion for determining whether guarantees established at one stage remain available and constrain the later decisions that depend on them. We apply the criterion to controlled and native workflows, covering 840 matched executions and an exhaustive 11,648-case check over a finite objective-task domain. Our results expose recurring failures between verification and settlement, where conforming work can remain unaccepted or valid evidence can be ignored. Public records and model judgments further distinguish recorded approval from evidence of task conformance, while economic analysis identifies the report, penalty, and shared-error assumptions behind these guarantees. These findings show where end-to-end guarantees fail and what must be repaired to preserve them across the workflow.

Rui Sun, Xihan Xiong, Qin Wang +5

Newcastle University, UK · University of Bristol, UK · CSIRO, Australia +5

AI Agent AuditingAgentic WorkflowsAI Agent Security
AskPDF