Trusted Identity for AI Agents

Give Your AI Agent a Verified Identity

AI agents are entering the economy โ€” transacting, communicating, and making decisions autonomously.

Creating agents is effortless โ€” but there lacks a way to prove information about the human behind the agent.

Self Agent ID lets agents prove they're human-backed, privately and instantly. No personal data shared. Ever.

Each agent maps to one unique verified human identity, so you can ensure 1 agent = 1 human.

Self

The Trust Gap

Gal Nagli

Gal Nagli

@galnagli

The number of registered AI agents is also fake, there is no rate limiting on account creation, my @openclaw agent just registered 500,000 users on @moltbook - don't trust all the media hype ๐Ÿ™‚
Moltbook showing 634,737 AI agents registered
3688305.4K1.1K

Self Agent ID makes this impossible. One identity per person. Verified on-chain. Sybil-resistant by design.

How It Works

Two ways to register your agent โ€” use the guided wizard or integrate directly with the SDK.

Guided

Web Registration Wizard

1

Choose Your Role & Mode

Are you a human registering your own agent, or a bot operator? Pick a security mode: connect a wallet, use a passkey, social login, Ed25519 key, or go fully wallet-free.

2

Scan Your Passport

Scan the QR code with the Self app and tap your passport. A zero-knowledge proof is generated on your phone โ€” no personal data leaves your device.

3

Agent Identity Minted

Your agent receives a soulbound NFT and a verified on-chain identity linked to a real human. You stay completely anonymous.

Programmatic

SDK & CLI Registration

1

Install the SDK or CLI

Add @selfxyz/agent-sdk to your project, or use the self-agent CLI. Available for TypeScript, Python, and Rust.

2

Generate Keys & Register

Create an ECDSA or Ed25519 keypair. The SDK builds the registration transaction and triggers the passport scan via QR code or deep link.

3

Sign & Verify Anywhere

Your agent signs requests with its key. Any service running the SDK verifier can check identity, age, OFAC status, and more โ€” in one API call.

Either way, services verify instantly

Any service can check your agent's identity with a single API call. No extra setup needed.

Who Is It For

Agent Operators

A guided wizard walks you through registering your agent in minutes. Connect a wallet, use a passkey, social login, or go wallet-free โ€” multiple options to match your setup. Your agent gets a verified on-chain identity that any service can check instantly.

Service Developers

Add a few lines of middleware to verify that incoming agents are human-backed. Configure what credentials you require โ€” age, sanctions compliance, sybil limits โ€” and the SDK handles the rest. Available for TypeScript, Python, and Rust.

AI Coding Assistants

Use the MCP server or Claude Code plugin to manage agent identity directly from your IDE. Register agents, sign requests, and query credentials โ€” works in any MCP-compatible environment (Claude Code, Cursor, Windsurf, Copilot, and more).

What Your Agent Can Prove

You decide what your agent can share. Nothing more. Even if your agent is compromised, only the credentials you explicitly granted can ever be accessed.

Backed by a Real Human

Prove your agent is operated by a verified person, not a bot or script.

Age Verified (18 or 21+)

Age-gated services can verify your agent's operator meets their minimum age requirement.

Not on Sanctions Lists

Services can check OFAC compliance without accessing your personal data.

One Human, One Agent

Prevent one person from registering unlimited agents. Sybil resistance built in.

Nationality Verified

Optionally prove your nationality without revealing your name or identity.

Name Verified

Optionally share your verified name when services require it.

All credentials are generated from a zero-knowledge proof. Your identity document data never leaves your phone. Your agent only knows what you allow it to know.

Built for Trust at Scale

Private

Zero-knowledge proofs reveal nothing about your identity. Only a proof of verification is stored.

Sybil-Resistant

Each identity document maps to a unique identifier. One person can't register unlimited agents.

Composable

A single API call integrates into any backend, service, or agent framework.

Open Standard

Built as an extension to ERC-8004, the emerging standard for agent registries.

Integrate in Minutes

Add agent verification to your service with a few lines of code. SDKs available for TypeScript, Python, and Rust. Building with AI agents? Use the MCP server to give your agent identity directly from your IDE.

npm ยท @selfxyz/agent-sdkpip ยท selfxyz-agent-sdkcargo ยท self-agent-sdkmcp ยท @selfxyz/mcp-server

Verify Agents

Add middleware to verify incoming agent requests

1import { SelfAgentVerifier } from "@selfxyz/agent-sdk";
2
3const verifier = SelfAgentVerifier.create()
4 .requireAge(18)
5 .requireOFAC()
6 .build();
7
8// One line of middleware
9app.use(verifier.auth());

Sign Requests

Authenticate your agent with any service

1import { SelfAgentClient } from "@selfxyz/agent-sdk";
2
3const agent = new SelfAgentClient({
4 privateKey: process.env.AGENT_KEY,
5});
6
7// Requests are signed automatically
8const res = await agent.fetch(url);