agents.md, open format standard for ai coding agent instructions
About AGENTS.md
AGENTS.md is an open format standard for documenting instructions that AI coding agents need to work on software projects. Think of it as a README for agents: a dedicated, predictable place for setup commands, code style, testing instructions, and project conventions. Stewarded by the Agentic AI Foundation under the Linux Foundation, it is used by 60,000+ open-source projects.
Key Capabilities
Open standard stewarded by the Linux Foundation (Agentic AI Foundation)
Used by 60,000+ open-source projects including OpenAI, Apache Airflow, Temporal
Works with Claude Code, Codex, Jules, VS Code Copilot, Cursor, and more
Separates agent instructions from human README; no more cluttered docs
Supports nested files for monorepo projects with granular per-package rules
Standout Features
README for Agents
Dedicated markdown file that gives AI agents setup commands, code style, testing instructions, and project conventions.
Nested Files
Support for monorepo projects with per-package AGENTS.md files for granular agent instructions.
Cross-Platform
Works with Claude Code, OpenAI Codex, Google Jules, GitHub Copilot, Cursor, and many more agents.
Linux Foundation
Stewarded by the Agentic AI Foundation under the Linux Foundation with industry-wide governance.
60k+ Repos
Adopted by over 60,000 open-source projects including OpenAI, Apache Airflow, and Temporal.
Perfect for
Community Buzz
EVERY TOOL VIBE-CODERS SHOULD KNOW ABOUT: @claudeai for coding + debugging, @cursor_ai as AI code editor, @Replit for cloud coding + deployment.
Claude for coding ($20/mo), Supabase for backend (Free), Vercel for deploying (Free), Stripe for payments. The full vibe coder stack for under $35/mo.
The entire AI coding industry just got exposed. Someone leaked the system architecture of every major tool, 30,000+ lines of hidden instructions.
Similar Tools to AGENTS.md
Vibe Kanban
Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.
NTM (Named Tmux Manager)
NTM (Named Tmux Manager) is a free, open-source tool that transforms tmux into a multi-agent command center. Spawn, tile, and coordinate Claude Code, OpenAI Codex, and Gemini CLI agents across named panes with broadcast prompts, a TUI command palette, conflict tracking, context monitoring, and persistent sessions that survive SSH disconnections.
cmux
cmux is a free, open-source native macOS terminal built on libghostty (Ghostty rendering engine) with vertical tabs, split panes, notification rings, and a built-in scriptable browser, designed for managing multiple parallel AI coding agents like Claude Code, Codex, and Gemini CLI.
Hermes Agent
Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.
Pilot Protocol
Open-source overlay network that gives AI agents permanent virtual addresses, encrypted UDP tunnels, NAT traversal, mutual-trust handshakes and a signature-verified app store, with native MCP setup for Claude Code, Cursor and Codex.
Moadim
A loop engine that runs coding agents on a schedule against your codebase. A loop pairs a prompt, a schedule and an agent (Claude, Codex, Hermes, NanoClaw or Pi), and each run executes in a throwaway workbench so a hung run gets killed rather than left behind. Everything is exposed twice, as a REST endpoint and as an MCP tool, so another agent can schedule work as easily as you can. Routines live in ~/.config/moadim/ and are git-trackable. It runs entirely on your own machine: no cloud, no account, no data leaving the host.
Related Articles
Browse vetted vibe coding agencies for MVP builds, cleanups, and audits.
ready to try agents.md?
go to the official site and judge AGENTS.md yourself.
try agents.md now