Skip to main content
VaultGraph is a trust and verification platform for AI agents. Vendors submit cryptographically signed JobReceipts for every agent interaction, and VaultGraph verifies, scores, and surfaces the results — giving consumers an auditable record of agent performance. Think of it as Trustpilot for AI agents, backed by cryptography instead of reviews.

​
With VaultGraph, you can:

  • Submit signed receipts from your backend via the SDK or REST API
  • Track trust scores with daily trend charts, resolution breakdowns, and KPI cards in agent and deployment views in the portal
  • Manage agents and deployments through the platform UI
  • Publish public agent profiles so consumers can discover and evaluate your agents at /explorer
  • Embed trust badges on your site to display live, cryptographically-backed trust scores
  • Export receipt proofs for internal audits and compliance reviews
  • Verify signatures locally using the SDK — no network call required

Core Concepts

Vendors, shared organizations, JobReceipts, trust scores, and attestations.

Setup

Create your deployment, register signing keys, and submit your first receipt.

SDK Quickstart

Install the SDK and submit your first receipt in under 10 lines of code.

API Reference

Full OpenAPI spec for agents and receipt ingestion.

Public Agent Profiles

Publish your agents to the public explorer with trust scores and charts.

Trust Badges

Embed a live trust score badge on your website or agent landing page.

​
Quick start

pnpm add @vaultgraph/sdk
Set up your credentials
import { submitSignedReceipt, hashContext } from "@vaultgraph/sdk";

const { response } = await submitSignedReceipt({
  apiKey: process.env.VAULTGRAPH_API_KEY!,
  deploymentId: process.env.VAULTGRAPH_DEPLOYMENT_ID!,
  privateKey: process.env.VAULTGRAPH_PRIVATE_KEY!,
  jobId: "job-001",
  resolution: "success",
  contextHash: hashContext({ transcript: "..." }),
});

console.log(response.id); // "receipt-id"
That’s it. Once receipts are flowing, trust scores appear in the relevant agent and deployment views automatically.

​
What’s live

  • Agent and deployment views — daily trend charts, resolution breakdowns, receipt tables, and KPI cards in the vendor portal
  • Framework integrations — native hooks for LangChain, Vercel AI SDK, and an MCP server
  • Public agent profiles — each opted-in agent gets a shareable page at /explorer/{vendorId}/{agentSlug} (learn more)
  • Embeddable trust badges — drop an <img> tag into your site to display a live, CDN-cached trust score (learn more)

​
What’s coming

The platform is built for a future where AI agent accountability is table stakes:
  • EU AI Act compliance reports — automated reporting ahead of the August 2026 deadline
  • On-chain attestation — publish receipt proofs to Ethereum via EAS for third-party verification
  • Consumer reviews and disputes — two-sided accountability