# agentsmd/agents.md

AGENTS.md — a simple, open format for guiding coding agents

Repository: https://github.com/agentsmd/agents.md
Canonical: https://ross.abutalabs.com/products/agentsmd
Homepage: https://agents.md
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-25T16:41:55+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 27
- inputs: {"age_days": 379, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 23919, forks 1807 (observed 2026-08-28T04:11:35.459142+00:00)

## What it is
AGENTS.md is a simple, open markdown format for giving AI coding agents project-specific context and instructions, like a README for agents. The repository hosts the specification plus a Next.js website with examples, and the format is adopted by many AI coding tools such as Codex, Cursor, and Gemini CLI.

## Use cases
- give AI coding agents build and test instructions for my repo
- standardize agent instructions across multiple AI coding tools
- keep READMEs clean while providing agent-focused context
- document code style conventions for AI assistants
- set up a predictable instruction file for Codex or Cursor
- share dev environment tips with coding agents

## When to choose
- you use AI coding agents and want a tool-agnostic, open instruction format
- you want one instruction file compatible with many agents like Codex, Cursor, and Devin
- your README is cluttered with agent-specific build and test details

## When to avoid
- you need a proprietary agent-specific config format required by a particular tool
- you want executable agent automation rather than static markdown instructions
- your project has no AI coding agent usage

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, developer-tools, agent-framework, prompt-engineering
- domain: developer-tools, artificial-intelligence, documentation
- platform: cross-platform
- tags: agents-md, coding-agents, specification, open-format, ai-assistants, ai-agents

## Member repositories
- agentsmd/agents.md (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:35.459142+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:19.007560+00:00, confidence not recorded.
  - readme: https://github.com/agentsmd/agents.md (fetched 2026-08-28T04:11:35.459142+00:00, sha 60ec51c22656)
  - homepage: https://agents.md (fetched 2026-08-29T07:54:08.545946+00:00, sha abcd92f2732a)
- Data as of 2026-08-30T08:39:29.467469+00:00.