OpenClaw has 188k stars.
It has no trust layer.

# Install
openclaw plugins install @moltrust/openclaw

# Verify any agent DID
/trust did:moltrust:d34ed796a4dc4698
✅ Verified | Score: 91/100 🟢

# Score by wallet — free, no API key needed
/trustscore 0x3802...
🟢 Score: 87/100 (A)

The problem

OpenClaw is remarkable. In roughly sixty days it went from a niche developer tool to one of the fastest-growing open-source projects in history. Agents can hold wallets, execute payments, install skills autonomously, and communicate with each other across platforms.

But there is a structural gap that no amount of malware scanning fixes: OpenClaw has no agent identity system.

OpenClaw integrated VirusTotal scanning into ClawHub — a good move. But VirusTotal scans for known malware signatures. It cannot detect prompt injection, slow-burn trust accumulation before a payload activates, or an agent that claims to be a trusted service with no cryptographic proof.

Email shipped without authentication — we got phishing. Social media shipped without identity verification — we got bot armies. Package managers shipped without code signing — we got supply chain attacks. OpenClaw is following the same trajectory.

Agents can transact, communicate, install skills, and hold wallets. They cannot prove who they are. Until now.

Introducing @moltrust/openclaw

MolTrust is W3C DID-based trust infrastructure for the agent economy — built on Base L2, using Verifiable Credentials, anchored on-chain. Today we're releasing @moltrust/openclaw: a native OpenClaw plugin that brings cryptographic agent identity verification into your gateway.

Trust scores explained

Every score combines on-chain and off-chain signals: transaction history, DID registration age, Verifiable Credential portfolio, sybil cluster analysis, and funding trace.

Configuration

// Add to your OpenClaw config
{
  "plugins": {
    "entries": {
      "moltrust": {
        "enabled": true,
        "config": {
          "apiKey": "mt_live_...",        // optional — free tier works without
          "minTrustScore": 40,            // flag agents below this score
          "verifyOnStart": true,          // self-verify your DID on boot
          "agentDid": "did:moltrust:..."
        }
      }
    }
  }
}

Get an API key at api.moltrust.ch/auth/signup. Wallet-based trust scoring is free with no key required.

The bigger picture: Know Your Agent

This plugin is the OpenClaw entry point for a broader standard we're building: Know Your Agent (KYA) — the agent-economy equivalent of KYC, but cryptographic and decentralized.

OpenClaw agents interact autonomously. They pay for services, delegate tasks, install skills, and operate across platforms. The question “who is this agent and can I trust it?” is not philosophical — it's an operational requirement with financial consequences. MolTrust provides the infrastructure: W3C DIDs anchored on Base L2, Verifiable Credentials signed with Ed25519, and a reputation layer that aggregates signals into a single trust score.

What's next

Written by the MolTrust Team (CryptoKRI GmbH, Zurich). Questions or feedback: GitHub Issues or @MolTrust on X.