AIAny
AI Agent2025
GitHub

AGENTS.md

Defines a predictable repository-level instruction file for coding agents, giving teams one place to document workflow rules instead of each tool inventing its own context format.

Introduction

Coding agents are only as useful as the project context they can reliably find. AGENTS.md makes instructions visible, versioned, and shared in the same way README files made human onboarding predictable.

What Sets It Apart

The format is deliberately small: build commands, testing expectations, architecture notes, and contribution rules can live in a file that many agents discover without custom integration. Its restraint is the point; it is a convention layer, not a policy engine.

Who Should Use It

Great fit if a repository is touched by several AI coding tools or has conventions agents often miss. Look elsewhere for enforceable access control, sandboxing, or task orchestration.

Information

  • Websitegithub.com
  • OrganizationsAgentic AI Foundation
  • Authorsagentsmd (repository owner), romainhuet
  • Published date2025/08/19

Categories

More Items

GitHub
AI Agent2026

Runs a local-first AI agent runtime that drives your desktop and automates workflows — browsing, file edits, approved shell commands, document extraction, and scheduled tasks — while integrating local or cloud LLMs (llama.cpp/TurboQuant) and embedding as an HTTP service or Tauri sidecar.

GitHub
AI Agent2026

Browser-based agent workspace and sandboxed app platform that lets organizations run AI agents to perform tasks and build shareable 'Gadgets'. Uses Gatekeepers for fine-grained, zero-trust access control and runs on Cloudflare Workers with multi-LLM support.

GitHub
AI Agent2026

Lets AI agents use a user's logged-in Chromium browser to read pages, fill forms, capture screenshots, and debug web workflows in an isolated Agent Window so the user's normal browsing is not interrupted.