# Agent Readability Spec (ARS) vs AGENTS.md

The map lists them as complementary: sites and agents commonly implement both.

[4 Read](/category/read/) [Agent Readability Spec](/protocols/vercel-agent-readability/) · [4 Read](/category/read/) [AGENTS.md](/protocols/agents-md/)

|  | [Agent Readability Spec](/protocols/vercel-agent-readability/) ARS | [AGENTS.md](/protocols/agents-md/) |
| --- | --- | --- |
| Lifecycle step | 4 Read: Give me the content | 4 Read: Give me the content |
| Answers | How readable is this site's content for AI agents, and what specifically should be fixed? | What build, test, and convention instructions should a coding agent follow in this repository? |
| Governed by | Vercel; published in Vercel's own Knowledge Base with no external standards process | Agentic AI Foundation (AAIF), a Linux Foundation project |
| Status (issuer's words) | A specification and scoring checklist, not a protocol; framed as best practices to implement voluntarily | "An open format... regardless of which coding agent you use"; explicitly not proprietary to any one tool |
| Version | current (last updated 2026-03-23 per a secondary source; no version number or publication date is given on the page itself) (2026-03) | current site guidance (living document) (2026-09) |
| Form / transport | document format | well-known file |
| Found at | none | AGENTS.md |
| Implementation | shipping | multi-implementation — agents.md (site claims over 60,000 AGENTS.md files across open-source GitHub repositories, via a path:AGENTS.md NOT is:fork NOT is:archived code search) |
| Evidence | 2 reported, 1 verified | 2 reported, 1 verified |
| Primary use case | Serve readable content to agents | Serve readable content to agents |
| Last verified | 2026-10-23 (current) | 2026-10-23 (current) |
| Specification | [https://vercel.com/kb/guide/agent-readability-spec](https://vercel.com/kb/guide/agent-readability-spec) | [https://agents.md](https://agents.md) |

## When to use which

- Choose Agent Readability Spec when your question is “How readable is this site's content for AI agents, and what specifically should be fixed?” and you accept its maturity: status "A specification and scoring checklist, not a protocol; framed as best practices to implement voluntarily", implementation shipping.
- Choose AGENTS.md when your question is “What build, test, and convention instructions should a coding agent follow in this repository?” and you accept its maturity: status ""An open format... regardless of which coding agent you use"; explicitly not proprietary to any one tool", implementation multi-implementation (agents.md (site claims over 60,000 AGENTS.md files across open-source GitHub repositories, via a path:AGENTS.md NOT is:fork NOT is:archived code search)).

Guidance is derived from the two records (question, status, implementation, prerequisites, pairings), not from opinion. Each record's page carries its numbered references.

## Read the full articles

- [Agent Readability Spec](/protocols/vercel-agent-readability/): How readable is this site's content for AI agents, and what specifically should be fixed?
- [AGENTS.md](/protocols/agents-md/): What build, test, and convention instructions should a coding agent follow in this repository?

Ask the MCP server to compare any two: the compare-protocols prompt, or get on both ids. [Connect](/connect/).

[vercel-agent-readability.json](/data/protocols/vercel-agent-readability.json) · [agents-md.json](/data/protocols/agents-md.json) · [Markdown](/compare/vercel-agent-readability-vs-agents-md/index.md)