AGENTS.md
A Markdown file at the root of a repository that gives AI coding agents the context and instructions a new teammate would need, kept separate from the human README.
Canonical text: https://agents.md/. In use on this site: github.com/manifesto-md/manifesto.md/blob/main/AGENTS.md.
How to use AGENTS.md
- A simple, open format for guiding coding agents.
- Think of AGENTS.md as a README for agents, a dedicated, predictable place to provide the context and instructions to help AI coding agents work on your project.
- README.md files are for humans, quick starts, project descriptions, and contribution guidelines; AGENTS.md complements this by containing the extra, sometimes detailed context coding agents need.
- Create an AGENTS.md file at the root of the repository.
- Cover what matters; add sections that help an agent work effectively with your project, such as project overview, build and test commands, code style guidelines, testing instructions and security considerations.
- Commit messages or pull request guidelines, security gotchas, large datasets, deployment steps, anything you'd tell a new teammate belongs here too.
- Large monorepo? Use nested AGENTS.md files for subprojects; agents automatically read the nearest file in the directory tree, so the closest one takes precedence.
- There are no required fields; AGENTS.md is just standard Markdown.
- The closest AGENTS.md to the edited file wins; explicit user chat prompts override everything.
- Will the agent run testing commands found in AGENTS.md automatically? Yes, if you list them.
- Treat AGENTS.md as living documentation.
- One AGENTS.md works across many agents.
Facts
- Maintainer
- Agentic AI Foundation, under the Linux Foundation
- Repository
- https://github.com/agentsmd/agents.md
- Licence of the text
- MIT
- Status of the text
- stable
- Listing
- listed, not yet claimed
Read with
- claimed
12-Factor AI-enabled CLI
Twelve testable factors for a command-line tool whose operator may be a human or an AI agent, from machine-readable capabilities to meaningful exit codes, with a conformance gate.
v0.1 Agentic Stack -
The /llms.txt file
A proposal for a Markdown file at /llms.txt that gives language models a curated overview of a website and links to clean Markdown versions of its pages.
-
Model Context Protocol
An open protocol, built on JSON-RPC, for connecting LLM applications to external data sources and tools through hosts, clients and servers.
Badge
[](https://manifesto.md/agents-md/) Maintainers claim a listing with a pull request setting listing: claimed, or a yes on the listing issue.