AGENTS.md: An Open Format for Guiding AI Coding Agents in Open-Source Projects
Slow-proofed and worth the wait. Worth its weight in flour.
Summary
AGENTS.md is a simple, open format for guiding AI coding agents, functioning as a README specifically designed for agents rather than humans. It provides a dedicated place to offer context and instructions to help AI coding agents work on a project. The format includes setup commands, code style guidelines, and other project-specific instructions. It has been adopted by over 60,000 open-source projects and is hosted on GitHub.
Key quotes
· 3 pulledThink 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 guides.
A simple, open format for guiding coding agents, used by over 60k open-source projects.
You might also wanna read
AGENTS.md: Standardized Format for AI Coding Agent Instructions in Software Projects
AGENTS.md is an open format specification that provides standardized instructions for AI coding agents to work on software projects, similar
AGENTS.md: Standardized Documentation Format for AI Agents Adopted by Major Platforms
The article introduces AGENTS.md, a standardized format for AI agents that serves as a structured alternative to human-readable README files
GitAgent: Open Standard for Portable AI Agent Definitions in Git Repositories
GitAgent by Lyzr is an open standard that extracts AI agent configurations, logic, tools, and memory into portable, version-controlled defin
GitAgentProtocol (GAP): An Open Standard for Running AI Agents Natively in Git
GitAgentProtocol (GAP) is introduced as an open standard for defining, versioning, and running AI agents natively within git repositories. I
gitagent.sh·2mo agoETH Zurich Research Questions Effectiveness of AGENTS.md Files for AI Coding Agents
ETH Zurich researchers published a paper challenging the value of AGENTS.md files for AI coding agents, finding they often hinder rather tha
Study finds well-written AGENTS.md files significantly boost AI code generation, while poor ones hurt performance
A systematic study of AGENTS.md files across a monorepo reveals that well-crafted files can dramatically improve AI code generation quality
