auth.md standardizes autonomous agent web registration

// 1h agoOPENSOURCE RELEASE

auth.md standardizes autonomous agent web registration

The auth.md protocol establishes a machine-readable Markdown specification and standardized HTTP endpoints for autonomous AI agent discovery, registration, and authentication. The standard aims to eliminate manual sign-up forms and browser-based OAuth flows in favor of automated machine-to-machine connections.

// ANALYSIS

By shifting agent authentication from manual browser interactions to discoverable Markdown files and standardized API endpoints, auth.md addresses a major architectural bottleneck for autonomous workflows. However, the protocol's real-world impact hinges entirely on broad adoption by web platforms and agent SDKs.

–Establishes clear pathways like Agent Verified (ID-JAG) and User Claimed (OTP) flows to balance system security with automation.
–Leverages RFC 9728 for Protected Resource Metadata, easing integration into existing enterprise OAuth frameworks.
–Removes human-in-the-loop requirements, enabling agents to autonomously scale access to external services without human friction.
–Supported at launch by developer-centric platforms like Cloudflare, Resend, and Firecrawl, indicating strong early momentum.

// TAGS

auth.mdagentsecurityapiopen-source

DISCOVERED

1h ago

2026-06-20

PUBLISHED

1h ago

2026-06-20

RELEVANCE

8/ 10

AUTHOR

Theo - t3․gg

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCEjust now

Builder.io has open-sourced agent-native, a framework designed to build applications that humans and AI agents can navigate and manipulate using the same shared state and tools.

agent-native is an open-source framework created by Builder.io that provides the essential primitives to build applications natively designed for both human and AI agent interaction. Rather than treating AI as a superficial chatbot wrapper, the framework establishes a unified application model where agents and users interact with the same underlying state, data, actions, and permissions. It offers SQL-backed state synchronization, support for modular tools or skills, robust memory management, and observability to monitor agent behavior. This architecture aims to make agentic SaaS interactions more reliable, deterministic, and deeply integrated.

MODEL49m ago

GLM-5.2 performance rivals Claude and GPT-5.5

Z.ai has launched GLM-5.2, a flagship open-weights large language model featuring a 1-million-token context window for long-horizon coding and agentic workflows. Early testing compares its performance favorably to proprietary frontier models like Claude Opus 4.8 and GPT-5.5, achieved via an efficient 'IndexShare' architecture.

NEWS1h ago

The HyperFrames team is coming to Tokyo to present their latest Claude Code skills and best practices for programmatic video generation.

Bin Liu, VP of Product and Agent Engineering at HeyGen, announced that the HyperFrames team is visiting Tokyo to present their latest Claude Code skills and best practices. HyperFrames is an open-source framework that enables programmatic video generation using web technologies like HTML, CSS, and GSAP, allowing AI coding agents to easily compose and edit videos.