AGENTS.md

A simple, open Markdown format for giving AI coding agents project-specific context and instructions, like a README aimed at agents rather than people.

Agent skills

Visit website agents.md

AGENTS.md is a simple, open format for guiding coding agents. It works like a README written for agents instead of people: a dedicated, predictable place in a repository to provide context and instructions that help an AI coding agent work on the project.

The repository also includes a Next.js website, hosted at agents.md, that explains the format's goals and shows examples.

The website runs locally with pnpm install and pnpm run dev, and is written in TypeScript under the MIT license.

More in Agent skills

See all 581

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents
github.com
A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.
- Agent skills
Vitruvius
github.com
An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.
- Agent skills
- AI evals

More in Agent skills

Provenance gate

Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

Vitruvius

Cookies