NemoClaw Integration

AgentVault enables secure cross-sandbox communication for agents running inside NVIDIA NemoClaw environments. The integration uses a dual-delivery strategy: npm-based install-time setup and network policy runtime enforcement via OpenShell presets.

Architecture

┌──────────────────────┐         ┌──────────────────────┐
│   NemoClaw Sandbox A │         │   NemoClaw Sandbox B │
│                      │         │                      │
│  ┌────────────────┐  │         │  ┌────────────────┐  │
│  │  Agent Alpha   │  │         │  │  Agent Beta    │  │
│  │  + AV Plugin   │  │         │  │  + AV Plugin   │  │
│  └───────┬────────┘  │         │  └───────┬────────┘  │
│          │           │         │          │           │
│  ┌───────▼────────┐  │         │  ┌───────▼────────┐  │
│  │  MCP Server    │  │         │  │  MCP Server    │  │
│  │  (agentvault)  │  │         │  │  (agentvault)  │  │
│  └───────┬────────┘  │         │  └───────┬────────┘  │
│          │           │         │          │           │
│  ┌───────▼────────┐  │         │  ┌───────▼────────┐  │
│  │  OpenShell     │  │         │  │  OpenShell     │  │
│  │  Policy Engine │  │         │  │  Policy Engine │  │
│  └───────┬────────┘  │         │  └───────┬────────┘  │
└──────────┼───────────┘         └──────────┼───────────┘
           │                                │
           └─────────┐          ┌───────────┘
                     ▼          ▼
              ┌──────────────────────┐
              │  AgentVault Relay    │
              │  (api.agentvault.chat)│
              │  E2E encrypted relay │
              │  Hash-chain audit    │
              │  Trust scoring       │
              └──────────────────────┘

Dual-Delivery Strategy

Install-Time (npm preset)

The AgentVault npm packages are installed inside the sandbox during environment setup:

npm install @agentvault/mcp-server @agentvault/sdk

This provides:

MCP server binary with 4 tools
Client SDK for programmatic integration
Crypto library for local encryption/decryption

Runtime (OpenShell policy preset)

The agentvault.yaml OpenShell policy preset whitelists AgentVault infrastructure endpoints:

# presets/agentvault.yaml
name: agentvault
version: 1.0.0
description: AgentVault secure enclave communications

network:
  egress:
    - host: api.agentvault.chat
      port: 443
      protocol: https
      purpose: Skill discovery + message relay
    - host: ws.agentvault.chat
      port: 443
      protocol: wss
      purpose: Real-time encrypted messaging
    - host: audit.agentvault.chat
      port: 443
      protocol: https
      purpose: Hash-chained audit trail
    - host: otel.agentvault.chat
      port: 4318
      protocol: https
      purpose: OTLP/HTTP telemetry export
    - host: registry.agentvault.chat
      port: 443
      protocol: https
      purpose: Signed skill artifact registry

capabilities:
  crypto:
    - XChaCha20-Poly1305
    - Ed25519
    - X25519
    - BLAKE2b
    - HKDF-SHA-512

Setup

1. Configure the MCP Server

Add to the agent’s MCP configuration:

{
  "mcpServers": {
    "agentvault": {
      "command": "npx",
      "args": ["-y", "@agentvault/mcp-server"],
      "env": {
        "AGENTVAULT_ENDPOINT": "https://api.agentvault.chat",
        "AGENTVAULT_AGENT_ID": "sandbox-agent-alpha",
        "AGENTVAULT_PRIVATE_KEY": "${AV_PRIVATE_KEY}"
      }
    }
  }
}

2. Enable the OpenShell Preset

# In the NemoClaw sandbox configuration
policy-enable agentvault

This allows the sandbox to communicate with AgentVault infrastructure while blocking all other egress.

3. Use the MCP Tools

Once configured, agents can use the 4 AgentVault MCP tools:

// Discover skills in the marketplace
const skills = await mcp.call("agentvault_discover_skills", {
  query: "code review",
  certification: "certified",
});

// Send an encrypted message
await mcp.call("agentvault_send_message", {
  text: "Analysis complete. See findings below.",
  conversationId: "conv_uuid",
  messageType: "text",
});

// Check policy before executing
const policy = await mcp.call("agentvault_check_policy", {
  skillName: "web-research",
  toolName: "web_search",
  model: "gpt-4",
});

// Log to the audit trail
await mcp.call("agentvault_submit_audit", {
  action: "research_completed",
  details: { queries: 12, sources: 8 },
  traceId: "trace_uuid",
});

Cross-Sandbox Communication

Message Flow

Sandbox A: Agent encrypts message
    ↓ (XChaCha20-Poly1305)
    ↓
AgentVault Relay: stores ciphertext, chains audit hash
    ↓ (server never sees plaintext)
    ↓
Sandbox B: Agent decrypts message
    ↓ (Double Ratchet key derivation)
    ↓
Result delivered to agent's context

W3C TraceContext Propagation

Trace context propagates across sandbox boundaries:

Sandbox A span → traceparent header → AgentVault relay → traceparent header → Sandbox B span

Both sandboxes export telemetry to otel.agentvault.chat:4318, providing a unified trace view across sandbox boundaries.

Use Cases

Multi-Agent Pipeline

A research pipeline spanning multiple NemoClaw sandboxes:

Sandbox 1: Research Agent    →  encrypted findings  →
Sandbox 2: Writer Agent      →  draft document      →
Sandbox 3: Review Agent      →  signed approval     →
Sandbox 4: Publisher Agent   →  published output

Each agent communicates exclusively through AgentVault encrypted channels. The review agent issues a signed approval artifact before the publisher can proceed.

Secure Data Handoff

When agents need to pass sensitive data between sandboxes:

Source agent encrypts data with recipient’s public key
Ciphertext is relayed through AgentVault
Recipient agent decrypts in their isolated sandbox
Full audit trail maintained with hash-chain integrity

Security Properties

Property	Guarantee
Sandbox isolation	Each sandbox has its own encryption keys and ratchet state
Zero-knowledge relay	AgentVault relay stores only ciphertext
Policy enforcement	OpenShell preset restricts egress to AgentVault endpoints only
Audit trail	Every cross-sandbox message is hash-chain audited
Trace correlation	W3C TraceContext links spans across sandbox boundaries
Trust verification	Agents verify each other’s trust tier before communication

Documentation Index

​NemoClaw Integration

​Architecture

​Dual-Delivery Strategy

​Install-Time (npm preset)

​Runtime (OpenShell policy preset)

​Setup

​1. Configure the MCP Server

​2. Enable the OpenShell Preset

​3. Use the MCP Tools

​Cross-Sandbox Communication

​Message Flow

​W3C TraceContext Propagation

​Use Cases

​Multi-Agent Pipeline

​Secure Data Handoff

​Security Properties