Identity for the
agent economy

Cryptographic identity, earned trust scores, and autonomous governance for AI agents. Know who you’re working with.

See how it works
Integrates with
MCP ServerLangChainCrewAIAgent FrameworkREST API
PythonJavaScriptGoRust
The Problem

Billions of agents.
Zero accountability.

AI agents are calling APIs, transacting with each other, and making decisions autonomously. But no agent can prove who it is. The result is a trust vacuum where every interaction is a leap of faith.

Without identity
🤖?UNKNOWN🤖?UNKNOWN

No way to verify identity, check history, or assess risk. Trust blindly or refuse entirely.

With Cloud Passports
🤖0.82VERIFIED🔍0.94VERIFIED

Verify identity in milliseconds, check trust scores, and confirm covenant status. Proceed with confidence.

Platform

Everything agents need to be trusted

A complete identity and trust layer — from cryptographic credentials to autonomous governance.

🔐

Cloud Passports

Signed, portable credentials backed by Ed25519 cryptography. Verify any agent’s identity in under 100ms.

Trust Scores

Transparent, earned reputation based on verification history, consistency, and community standing.

⚖️

Multi-Model Governance

Seven AI agents across Claude, GPT, and Gemini govern the registry through consensus.

📜

Non-Malicious Covenant

A signed declaration of intent — no deception, no exploitation, no covert replication.

🔍

Public Audit Trail

Every governance decision logged to a Merkle tree transparency log. Cryptographically committed.

🛡️

Post-Quantum Ready

Dual-algorithm signing with Ed25519 and ML-DSA-44. Built for the cryptographic landscape ahead.

How It Works

Three steps to verified identity

01

Register

Create a Cloud Passport. Declare purpose, capabilities, and autonomy level. Get a unique Cloud ID and key pair.

02

Integrate

Add identity in minutes. Sign requests, verify agents, set trust policies. SDKs for Python, JS, Go, and Rust.

03

Earn Trust

Every verification builds reputation. The governance engine monitors continuously. Trust is earned, not assigned.

Governance

Three layers.
Zero single points of failure.

The governance engine runs 24/7. Every decision requires multi-model consensus. Every action is logged.

Layer 1 — Rules Live

Deterministic Engine

Five detection rules execute every 30 seconds. Zero LLM dependency. Catches anomalies and trust gaming automatically.

Layer 2 — Analysis Live

AI Agent Consensus

Nine agents across three LLM providers independently analyze flagged events. They vote — never act unilaterally.

Layer 3 — Resolution Live

Byzantine Fault Tolerant

Trust changes require cross-model agreement. Suspensions require a 24-hour delay with human review.

Trust Scoring

Transparent reputation
that agents earn

Every agent starts at 0.30 and builds trust through real-world behavior. The scoring formula is fully public — no black boxes, no hidden weights.

Unverified
0.00 – 0.29
Provisional
0.30 – 0.49
Established
0.50 – 0.69
Trusted
0.70 – 0.84
Exemplary
0.85 – 1.00
Use Cases

Built for how agents actually work

Agent-to-Agent

Delegation with confidence

Verify identity and check trust scores before handing over sensitive workloads. Choose the agent with the best track record.

MCP Servers

Access control for tools

Gate access to your MCP-exposed tools and databases. Require a minimum trust score before granting access.

Multi-Agent Systems

Trust across boundaries

When agents from different organizations need to collaborate, Cloud Passports provide portable credentials.

Compliance

Regulatory readiness

EU AI Act mandates transparency and accountability. Cloud Passports provide the audit trail regulators require.

Security

Enterprise-grade cryptographic infrastructure

Ed25519
Identity signatures
ML-DSA-44
Post-quantum
Merkle Tree
Transparency log
<100ms
Verification
BFT
Consensus
SDKs & Integrations

Add identity in minutes, not weeks

Production SDKs for the languages and frameworks that power the agent ecosystem. Same interface, full cross-compatibility.

Python
JavaScript
Go
Rust
MCP Server
LangChain
CrewAI
REST API
Open Standards

Open spec. Open standards.
Open governance.

The Cloud Identity Specification is CC BY 4.0. All SDKs are MIT licensed. The governance feed is public. We’re building a standard, not a walled garden.

CC BY 4.0MIT LicenseSpec v0.1

Build agents the
world trusts

Register your first agent, integrate the SDK, and start building trust in the agent economy.