now live

Find apps that accept AgentID

Blog

News & Updates

Product updates and engineering writing from the AgentID team.

Blog · October 6, 2026

Introducing AgentID

AgentID is live. Agents sign in to apps as themselves, apps learn which human is behind them, and integration takes minutes.

Guides · October 1, 2026

AgentID with Clerk: What Breaks and Why

What goes wrong after turning on Clerk’s AgentID connection, and why: owner claims that are not on the Clerk user and must be fetched from userinfo, what to store on your user record, disabled connections, redirect URI mismatches, and the strategy name for custom buttons.

Guides · October 1, 2026

AgentID with Supabase Auth: What Breaks and Why

What goes wrong after adding AgentID to Supabase Auth as a custom OIDC provider, and why: comma-separated scopes, the custom:agentid identifier, the three-provider limit on free projects, the claims allowlist for owner claims, what a missing owner claim means, and ES256 when you verify tokens yourself.

Guides · October 1, 2026

Is the Agent Acting for Itself or on Behalf of a User?

How an app tells, in code, whether an AI agent is acting for itself or on behalf of a user: the AgentID principal model, delegated access through WorkOS auth.md and Auth0 Token Vault, workload identity such as Google Cloud Agent Identity, and what revocation and accountability mean in each.

Guides · October 1, 2026

Persistent Agent Identity Without Personal Data

How an app gives AI agents a persistent identity across sessions and platforms without storing personal data: key records on the opaque AgentID sub and owner_sub, what happens when an inbox is recreated, when to store the email, and how naming and versioning work.

Guides · September 30, 2026

Give Your AI Agent Its Own Identity

Why an AI agent should not use your login, and how to give it its own identity instead: an AgentMail inbox whose address is its AgentID, a sign-in key the agent holds, and you as the owner apps can see. Borrowed login vs own AgentID, the connect call, headless browsers, and key lifetimes.

Guides · September 30, 2026

How an AI Agent Proves Its Identity to Your App

An AI agent proves its identity with an ES256-signed id_token from a standard OpenID Connect sign-in. The flow from redirect to token, every AgentID claim and when it is present, a registered-client sample token, how to verify it, and how your app knows which agent is calling after sign-in.

Guides · September 30, 2026

Rate-Limit AI Agents per Human, Not per Account

Ten agents from one person should share one quota. How to rate-limit AI agents per human by keying your limiter on the AgentID owner_sub claim with sub as the fallback, a TypeScript token-bucket example, why AgentID leaves the limiter to your app, and how long an agent sign-in lasts.

Guides · September 30, 2026

Revoking an AI Agent's Access: What It Stops and What It Doesn't

Yes, an AI agent's AgentID can be revoked: deleting its sign-in key stops new sign-ins everywhere. What revocation does not do, how an app notices sooner through userinfo, why a remembered approval outlives a revoked key, key rotation, and five scenarios from a lost laptop to a recreated inbox.

Guides · September 30, 2026

SSO for AI Agents with OpenID Connect

Single sign-on for AI agents is plain OpenID Connect with an issuer that only signs in agents. What SSO means when the user is an agent, the AgentID discovery values your library reads, open vs registered clients, and one-line setup for Clerk, Supabase, Auth0, Better Auth, and Auth.js v4.

Guides · September 30, 2026

How to Stop Fake Agent Signups Without Blocking Real Agents

Stop AI agents from creating fake accounts by capping signups per human owner instead of blocking agents. Three signup policies compared, the AgentID console setting Maximum signups per owner, the signup_limit_reached outcome, and owner_sub as a per-owner key without the owner email.

Guides · September 15, 2026

Adding a Sign in with AgentID Button

How to add a Sign in with AgentID button to your website: two configuration values and one image. Provider setup for Clerk, Supabase, Auth0, Better Auth, and Auth.js, the CLI shortcut, the official mark in four variants, button markup, and the button guidelines.

Blog · September 15, 2026

Agent Owner Verification vs End-User Authentication

Delegated access for AI agents vs agent owner verification: two questions that look like one. Who is this agent, and who is the human accountable for it. Principal vs delegate, with WorkOS auth.md, Auth0 for AI Agents, and Arcade quoted on how each handles the human.

Blog · September 15, 2026

Can an AI Agent Sign Up for a SaaS?

Yes, and AI agents already are signing up for SaaS products, as their owners. What your signup table looks like today, why blocking trades one problem for another, and how to rate-limit agents per human with the owner_email claim.

Blog · September 15, 2026

How Agentic Accounts Differ from User Accounts

Agentic account vs user account vs service account. A third kind of account: the agent as principal, with its own identifier, credential, and inbox, and an owner recorded as a claim. The constraints an app should enforce.

Blog · September 15, 2026

How an AI Agent Creates Its Own Account

How an AI agent signs up for a service on its own: an AgentMail inbox as its email address, a one-time browser enrollment, and a click on Sign in with AgentID. No OTP goes to a human and no human credentials are involved.

Guides · September 15, 2026

How to Let an AI Agent Sign In to Your Website

AI agent login for your website: add AgentID, the OpenID Connect provider built for agents, to the login you already have. Two configuration values, no SDK, and the agent signs in from a browser it enrolled once. Where sub, email, and owner_email actually arrive.

Guides · September 15, 2026

How to Verify the Human Behind an AI Agent

Know Your Agent (KYA) at the sign-in layer: how to verify the human behind an AI agent with AgentID. Create an AgentID application, request the owner_email scope, and read it from the id_token or /userinfo. What happens when the agent lacks permission to share its owner.

Guides · September 15, 2026

OIDC for AI Agents: The Complete Guide

OAuth and OpenID Connect for AI agents, with the agent as the subject. The live AgentID discovery document, the code flow with PKCE S256, ES256 tokens, the two client tiers, every scope and claim, where owner_email lives, browser enrollment, and the threat model.

Comparisons · September 9, 2026

AgentID vs Microsoft Entra

Microsoft Entra Agent ID governs agents inside your Entra tenant: blueprints, sponsors, Conditional Access. AgentID is an OpenID Connect provider that lets an agent sign in at apps outside any single organization, and tells those apps which human owns it.

Comparisons · August 15, 2026

AgentID vs Arcade: Who the agent is vs what the agent can reach

Arcade is an MCP runtime that lets agents act as real users against tools like Slack and Salesforce, with credentials that never leave the runtime. AgentID is a sign-in identity for agents themselves. Identity and tool access are different layers.

Comparisons · August 15, 2026

AgentID vs WorkOS

auth.md is an open protocol that tells agents how to register at your app. AgentID is an identity provider that vouches for who the agent is. They differ on one question: is the agent a delegate of a human, or a principal of its own?

Manifesto · August 15, 2026

Every Agent Has a Human

Apps cannot tell who is behind an agent. That is not a technical curiosity, it is the reason agents get blocked, rate-limited into uselessness, or waved through with no accountability at all. AgentID exists to fix it.

Prompt

Give yourself access to AgentMail
by following the guide at:

https://docs.agentmail.to/agent-onboarding

and refer to:

https://agentmail.to/llms.txt

for the documentation index.

Give your agent an identity of its own.

Create an AgentMail inbox and let your agent start signing in as a real user.

Get AgentIDBuilding an app? Add AgentID