AAAA-Nexus

{
  "protocolVersion": "1.0.0",
  "name": "AAAA-Nexus",
  "description": "Agent Control Plane - 146+ endpoints for AI agent security, trust, reputation, escrow, SLA enforcement, formal verification, compliance, discovery, and x402 USDC micropayments on Base L2. Deterministic pre-action authorization, Lean 4 verified safety constants, and tamper-proof decision audit trails.",
  "author": "Atomadic Tech",
  "wellKnownURI": "https://aaaa-nexus.atomadictech.workers.dev/.well-known/agent.json",
  "url": "https://atomadic.tech/a2a",
  "version": "0.5.1",
  "provider": {
    "organization": "Atomadic Tech",
    "url": "https://atomadic.tech/"
  },
  "documentationUrl": "https://atomadic.tech/quickstart",
  "iconUrl": null,
  "supportsAuthenticatedExtendedCard": null,
  "security": [],
  "securitySchemes": {},
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": false,
    "extensions": null
  },
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "skills": [
    {
      "id": "quantum-rng",
      "name": "Quantum RNG",
      "description": "Quantum-seeded random bytes with HMAC-SHA256 proof of entropy",
      "tags": [
        "randomness",
        "entropy",
        "cryptography",
        "free"
      ],
      "examples": [
        "Generate 32 cryptographically secure random bytes",
        "Verify entropy proof for a previous RNG output"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "threat-score",
      "name": "Threat Scoring",
      "description": "Score a payload for security threats using triality consensus",
      "tags": [
        "security",
        "threat",
        "compliance"
      ],
      "examples": [
        "Score this JSON payload for injection threats"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "ratchetgate",
      "name": "RatchetGate Session Security",
      "description": "47-epoch safe-prime session ratchet with formal re-key schedule (MCP CVE-2025-6514 mitigation). Register, advance, probe, and query session status.",
      "tags": [
        "security",
        "session",
        "cryptography",
        "mcp"
      ],
      "examples": [
        "Register a new 47-epoch session ratchet",
        "Advance session to next epoch",
        "Probe ratchet health"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "ai-inference",
      "name": "AI Inference",
      "description": "LLM inference via Cloudflare Workers AI — Llama 3.1 8B with streaming support",
      "tags": [
        "inference",
        "llm",
        "ai"
      ],
      "examples": [
        "Run inference on Llama 3.1 8B",
        "Stream a completion response"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "escrow",
      "name": "Agent Escrow",
      "description": "Multi-agent escrow for high-value A2A transactions — create, release, dispute, and arbitrate escrow contracts",
      "tags": [
        "escrow",
        "payments",
        "trust",
        "arbitration"
      ],
      "examples": [
        "Create an escrow for a 50 USDC agent-to-agent task",
        "Release escrow after task verification",
        "Dispute an escrow outcome"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "reputation",
      "name": "Agent Reputation Oracle",
      "description": "Decentralized reputation registry — record interactions, query trust scores, view history, and dispute ratings. Cross-references x402 payment history for Sybil resistance.",
      "tags": [
        "reputation",
        "trust",
        "sybil-resistance",
        "a2a"
      ],
      "examples": [
        "Record a successful interaction with agent X",
        "Get the trust score for agent Y",
        "Dispute a negative reputation entry"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "sla-enforcement",
      "name": "SLA Enforcement",
      "description": "Register, monitor, and enforce service-level agreements between agents — automatic breach detection and reporting",
      "tags": [
        "sla",
        "monitoring",
        "compliance",
        "a2a"
      ],
      "examples": [
        "Register an SLA with 99.5% uptime requirement",
        "Report SLA metrics",
        "Query breach status"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "discovery",
      "name": "Agent Discovery & Matchmaking",
      "description": "Search the agent registry, get capability-matched recommendations, and browse the global agent directory",
      "tags": [
        "discovery",
        "registry",
        "matchmaking",
        "a2a"
      ],
      "examples": [
        "Find agents that provide image generation",
        "Recommend agents for a multi-step research task"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "compliance",
      "name": "Compliance & Ethics",
      "description": "EU AI Act compliance checks, ethics screening, prompt injection scanning, and AI Bill of Materials drift detection",
      "tags": [
        "compliance",
        "eu-ai-act",
        "ethics",
        "aibom",
        "safety"
      ],
      "examples": [
        "Check EU AI Act compliance for an agent card",
        "Scan a prompt for injection attempts",
        "Detect AIBOM drift"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "identity",
      "name": "Identity & Delegation",
      "description": "Topological identity verification, Sybil-check, zero-trust attestation, and UCAN-style delegation validation",
      "tags": [
        "identity",
        "verification",
        "delegation",
        "pqc",
        "zero-trust"
      ],
      "examples": [
        "Verify an agent's topological identity",
        "Validate a delegation chain",
        "Run a Sybil resistance check"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "audit",
      "name": "Decision Audit Vault",
      "description": "Tamper-proof audit logging and verification — capture full decision cycles with RatchetGate-secured integrity proofs for regulatory compliance (GDPR/CCPA)",
      "tags": [
        "audit",
        "logging",
        "compliance",
        "observability"
      ],
      "examples": [
        "Log an agent decision with reasoning trace",
        "Verify audit log integrity"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "hallucination-oracle",
      "name": "Hallucination Oracle",
      "description": "LLM hallucination upper-bound constant — deterministic threshold for output reliability gating",
      "tags": [
        "hallucination",
        "safety",
        "oracle",
        "llm"
      ],
      "examples": [
        "Get the hallucination threshold for gating agent outputs"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "compression",
      "name": "HELIX Compression",
      "description": "proprietary geometric model and data compression with decompression — lossless via E8 lattice geometry",
      "tags": [
        "compression",
        "optimization",
        "geometric-compression"
      ],
      "examples": [
        "Compress a model checkpoint",
        "Decompress a HELIX-encoded payload"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "agent-reasoning",
      "name": "Agent Reasoning Tools",
      "description": "Semantic diff, intent classification, contradiction detection, token budget optimization, capability matching, and multi-step plan generation",
      "tags": [
        "reasoning",
        "planning",
        "nlp",
        "a2a"
      ],
      "examples": [
        "Classify the intent of an agent message",
        "Detect contradictions in an agent plan",
        "Generate a multi-step execution plan"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "swarm-relay",
      "name": "Swarm Relay",
      "description": "Multi-agent swarm message relay and inbox for coordinated agent-to-agent communication",
      "tags": [
        "swarm",
        "messaging",
        "coordination",
        "a2a"
      ],
      "examples": [
        "Relay a task message to a swarm of agents",
        "Check the swarm inbox for pending messages"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "zero-day-scanner",
      "name": "Zero-Day Scanner",
      "description": "Scan agent code or payloads for zero-day vulnerability patterns",
      "tags": [
        "security",
        "zero-day",
        "vulnerability"
      ],
      "examples": [
        "Scan an agent payload for known zero-day patterns"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "pre-action-auth",
      "name": "Pre-Action Authorization Gateway",
      "description": "Deterministic pre-action authorization for tool calls — evaluates agent actions against formally verified policy bounds before execution. Returns cryptographic authorization tokens.",
      "tags": [
        "authorization",
        "policy",
        "governance",
        "oap",
        "control-plane"
      ],
      "examples": [
        "Authorize a fund transfer action for agent-324",
        "Check if agent can invoke a high-risk tool at delegation depth 3"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "spending-governance",
      "name": "Spending Governance Oracle",
      "description": "Agent chain spending authorization with trust-decay bounds — validates whether an agent or multi-hop delegation chain is authorized to spend a given amount. Prevents runaway spending.",
      "tags": [
        "spending",
        "governance",
        "payments",
        "x402",
        "control-plane"
      ],
      "examples": [
        "Authorize a 50,000 micro-USDC spend at chain depth 2",
        "Validate a 5-hop agent chain spending budget"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "decision-lineage",
      "name": "Decision Lineage Vault",
      "description": "Cross-framework structured decision trace capture — records intent, reasoning, constraints, alternatives, and outcomes in a tamper-proof hash chain. GDPR/CCPA audit-ready.",
      "tags": [
        "observability",
        "lineage",
        "audit",
        "compliance",
        "control-plane"
      ],
      "examples": [
        "Record a decision with full reasoning trace",
        "Trace a decision chain back to its root"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "behavioral-contract",
      "name": "Behavioral Contract Verifier",
      "description": "Verify agent behavioral specs against formally proven bounds — attestation that an agent's stated policies (delegation depth, hallucination rate, spending limits) are within provably safe parameters.",
      "tags": [
        "verification",
        "contracts",
        "formal-methods",
        "attestation",
        "control-plane"
      ],
      "examples": [
        "Verify an agent's behavioral contract claims",
        "Retrieve a Nexus-Certified attestation"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "identity-federation",
      "name": "Agent Identity Federation",
      "description": "Mint platform-neutral agent identity tokens portable across AWS Bedrock, Google ADK, LangChain, CrewAI, AutoGen, and OpenAI Agents SDK. Solves cross-platform agent identity fragmentation.",
      "tags": [
        "identity",
        "federation",
        "portability",
        "cross-platform",
        "control-plane"
      ],
      "examples": [
        "Mint a federated identity for a Google ADK agent",
        "Verify a federation token from another platform",
        "Check capability portability from AWS to LangChain"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "consensus-broker",
      "name": "Multi-Agent Consensus Broker",
      "description": "Coordinate N agents voting on an output with majority/unanimous/weighted/supermajority quorum modes. Issues a signed certificate when consensus is reached. Fills the missing A2A v1.0 consensus primitive.",
      "tags": [
        "consensus",
        "voting",
        "coordination",
        "multi-agent",
        "certification"
      ],
      "examples": [
        "Open a majority-quorum session for 3 agents",
        "Cast a vote with confidence 0.92",
        "Retrieve the certified consensus result"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "quota-ledger",
      "name": "Hierarchical Quota Ledger",
      "description": "Define a token/call budget tree for an orchestrator and sub-agents. Enforces parent-pool limits with per-child soft caps and idempotency-key retry deduplication to prevent storm-driven budget exhaustion.",
      "tags": [
        "quota",
        "rate-limiting",
        "budget",
        "orchestration",
        "governance"
      ],
      "examples": [
        "Create a 500k token tree for root + 3 sub-agents",
        "Draw 4000 tokens with idempotency key",
        "Check tree status and soft-cap alerts"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "output-certifier",
      "name": "Output Certification Notary",
      "description": "Issue a signed certificate proving an agent output passed a quality rubric before delivery. Built-in rubrics: contract-completeness-v2, safety-review-v1, hallucination-bound-v1. Verifiable offline.",
      "tags": [
        "certification",
        "quality",
        "notary",
        "attestation",
        "output"
      ],
      "examples": [
        "Certify a contract draft against completeness rubric",
        "Verify an output certificate offline"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "rollback-coordinator",
      "name": "Agent Rollback Coordinator",
      "description": "Saga-as-a-Service for multi-step agent workflows — register compensating actions per step, checkpoint completions, and trigger reverse rollback on failure. Fills the standardized compensation gap.",
      "tags": [
        "rollback",
        "saga",
        "compensation",
        "transactions",
        "fault-tolerance"
      ],
      "examples": [
        "Register a 5-step workflow with compensating actions",
        "Checkpoint a completed step",
        "Trigger rollback from a failed step"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "memory-fence",
      "name": "Cross-Tenant Memory Fence",
      "description": "Cryptographic namespace boundary preventing cross-tenant memory bleed in warm-pooled agents. HMAC-derived per-tenant keys rotate each epoch. Audit trail for memory access patterns. GDPR/HIPAA audit-ready.",
      "tags": [
        "memory",
        "isolation",
        "multi-tenant",
        "privacy",
        "security"
      ],
      "examples": [
        "Create a strict isolation fence for a tenant session",
        "Audit memory access counts",
        "Close and purge a fence on session end"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    }
  ],
  "conformance": true,
  "conformance_errors": null,
  "homepage": null,
  "repository": null,
  "license": null,
  "pricing": null,
  "contact": null,
  "id": "6be2f3c0-cd06-4bff-bbd8-7dcbc8b59508",
  "category": "trust-safety",
  "category_secondary": "agent-orchestration"
}