Andrey Markin
  • home
  • services
  • projects
  • blog
  • directory
    • Tool
    • Library
    • Repo
    • Article
    • XTweet
    • Guideline
    • Video
  • courses
  • resume
  • about
  • contact
  • meet

Mark Life Ltd

  1. Home
  2. Directory
  3. Agent Registration Auth Md
Meet

Mark Life Ltd

BG208147965

HomeContactPrivacyLLM-friendlyBlog RSSDirectory RSS
  1. Directory
  2. Agent Registration with auth.md
ArticleAIBackendagentssecurityauth

Agent Registration with auth.md

Open protocol for autonomous agents to self-register for services without human intervention — a standardized auth.md file + HTTP endpoints replace OAuth and sign-up forms.

Added May 28, 2026Published May 21, 2026Garrett Galow
Visit article

Proposes auth.md as a discovery document (published at https://yourservice.com/auth.md) paired with three HTTP endpoints (/agent-auth, /agent-auth/claim, /agent-auth/claim/complete) to let agents register without a human in the loop.

Two flows:

  • Agent Verified — trusted agent platforms sign ID-JAG assertions; services verify against provider JWKS and issue credentials synchronously
  • User Claimed — six-digit OTP sent to a user; anonymous pre-claim access allowed with limited permissions until claimed

Built on RFC 9728 (resource discovery), the IETF ID-JAG delegation draft, and OIDC backchannel logout for revocation. JWT validation reuses existing OIDC patterns (jose library in the Node.js example). Five implementation steps to add to an existing auth system.

Related

  • Logging SucksBoris Tane's argument that traditional logging is broken for distributed systems and that "wide events" — one comprehensive, high-cardinality structured event per request per service — are the fix. Log what happened to the request, not what your code is doing.
  • EveOpen-source agent framework from Vercel — define agents as directories of TypeScript and Markdown config and deploy them as standard Vercel projects.
  • FlueTypeScript framework for building durable AI agents and workflows with no vendor lock-in — write once, deploy anywhere, run on any LLM.
  • Learn Harness EngineeringA 12-lecture curriculum on building effective harnesses that enable AI agents to complete complex tasks reliably — covering architecture, state management, session continuity, and observability patterns.