AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Most stars first · from page 32Worked for most · soon

Kilo-OrgAGENTS.md

kilocode

Kilo-Org/kilocode/AGENTS.md

Kilo CLI is an open source AI coding agent that generates code from natural language, automates tasks, and supports 500+ AI models.

27k2mo agoDiscuss

OpenAIAGENTS.md

This directory contains the Elixir agent orchestration service that polls Linear, creates per-issue workspaces, and runs Codex in app-server mode. - Runtime config is loaded from WORKFLOW.md front matter via SymphonyElixir.Workflow and SymphonyElixir.Config. - Keep the implementation aligned with ../SPEC.md where practical. - The implementation may be a superset of the spec. - The implementation must not conflict with the spec. - If implementation changes meaningfully alter the intended behavior, update the spec in the same change where practical so…

27k7mo agoDiscuss

OthmanAdiAGENTS.md

planning-with-files

OthmanAdi/planning-with-files/AGENTS.md

For any agent doing releases, merges or issue work in this repository. The code and scripts/ are discoverable; this file holds the decisions that are not.

27k5d agoDiscuss

VercelAGENTS.md

ai

vercel/ai/AGENTS.md

This file provides context for AI coding assistants (Cursor, GitHub Copilot, Claude Code, etc.) working with the Vercel AI SDK repository. The AI SDK by Vercel is a TypeScript/JavaScript SDK…

27k38d agoDiscuss

VercelAGENTS.md

ai / apps

vercel/ai/apps/docs/AGENTS.md

This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ (resolved from this file's directory; in…

27k38d agoDiscuss

VercelAGENTS.md

ai / ai

vercel/ai/packages/ai/AGENTS.md

No summary in the file. Open it to read it.

27k38d agoDiscuss

deepset-aiAGENTS.md

haystack

deepset-ai/haystack/AGENTS.md

Haystack uses Hatch for environment and dependency management. Do not run python or pip directly. Before running code on this project, you must be able to run hatch --version and get a correct output. If not, ask the user where Hatch is or if they want to install it. For installation instructions, refer to https://hatch.pypa.io/latest/install/#installation. hatch -e test run python SCRIPT.py hatch -e test shell uv pip install PACKAGE hatch env prune Tests run via Hatch and support pytest arguments.

27k4mo agoReads credentialsDiscuss

deepset-aiAGENTS.md

haystack / docs-website

deepset-ai/haystack/docs-website/AGENTS.md

No summary in the file. Open it to read it.

27k4mo agoDiscuss

deepset-aiAGENTS.md

haystack / test

deepset-ai/haystack/test/AGENTS.md

No summary in the file. Open it to read it.

27k4mo agoReads credentialsDiscuss

phurynAGENTS.md

pm-skills

phuryn/pm-skills/AGENTS.md

All agent guidance for this repository lives in CLAUDE.md — that is the single source of truth. Please read CLAUDE.md before making changes. This file exists only so non-Claude agents that look for AGENTS.md are pointed to the same instructions; do not duplicate guidance here.

26k3mo agoDiscuss

MicrosoftAGENTS.md

winget-cli

microsoft/winget-cli/AGENTS.md

Follow .github/copilot-instructions.md for repository-specific development guidance. Before filing a GitHub issue in this repository: Before opening a pull request:

26k9d agoDiscuss

AnthropicAGENTS.md

knowledge-work-plugins / zoom-plugin

anthropics/knowledge-work-plugins/partner-built/zoom-plugin/AGENTS.md

Cross-platform discovery file for agent tools that look for AGENTS.md. This repository contains a Zoom developer plugin centered on SKILL.md-based workflows and reference material. Primary capabilities: - choose the right Zoom surface for a use case - plan Zoom integrations across REST APIs, SDKs, webhooks, OAuth, and MCP - debug broken Zoom integrations - build focused Zoom implementations for meetings, bots, chat, phone, contact center, and virtual agent workflows - provide deep product-specific reference material under skills/

26k8mo agoDiscuss

browserbaseAGENTS.md

stagehand

browserbase/stagehand/AGENTS.md

No summary in the file. Open it to read it.

25k52d agoDiscuss

EveryIncAGENTS.md

compound-engineering-plugin

EveryInc/compound-engineering-plugin/AGENTS.md

This repository is the root of the compound-engineering coding-agent plugin and the marketplace/catalog metadata used to distribute it. It also contains: - the Bun/TypeScript CLI that converts Claude Code plugins into other agent platform formats - shared release and metadata infrastructure for the CLI, marketplace, and plugin AGENTS.md is the canonical repo instruction file. Root CLAUDE.md is a symlink to AGENTS.md so Claude Code and other tools that look for CLAUDE.md still find it at the expected path. Keep that…

25k2mo agoDiscuss

agentskillsAGENTS.md

agentskills

agentskills/agentskills/AGENTS.md

Agent Skills is a small, portable, client-neutral format. Keep the format small: new requirements impose costs on every implementation and should address demonstrated interoperability needs, not hypothetical completeness. Use progressive disclosure in this repository too. Keep details in their natural source instead of repeating commands, configuration, or policy here. docs/specification.mdx is authoritative for format requirements. Explanatory documentation, examples, tests, and implementations do not add requirements to the format. Preserve the distinction between the format and choices made by skill authors,…

25k10mo agoDiscuss

activepiecesAGENTS.md

activepieces

activepieces/activepieces/AGENTS.md

Open-source AI-first workflow automation platform. Self-hosted or cloud. 400+ pieces. MCP support. - Multi-tenant: Platform → Projects → Users. ALL queries MUST filter by projectId or platformId. - Editions: CE…

25k4mo agoDeletes or force-pushesDiscuss

letta-aiAGENTS.md

letta

letta-ai/letta/AGENTS.md

main is intentionally a small landing page. The retired Letta V1 server source is preserved on the archive branch for historical reference only. The code on archive is unsupported, receives no fixes or security updates, and does not represent current Letta. The old letta/letta Docker image and the Python server packages associated with that code are retired as well. Do not use the archive branch, an old release or tag from this repository, the old Python server packages, or the…

25k46d agoDiscuss

Model Context ProtocolAGENTS.md

python-sdk

modelcontextprotocol/python-sdk/AGENTS.md

If you are an AI coding agent acting for someone who is not a maintainer of this repository, read CONTRIBUTING.md before opening issues or pull requests here. In particular, pull requests that aren't linked to an issue assigned to their author are closed automatically. - main is the current stable line (v2); releases are cut from it (see RELEASE.md). - v2 is released; its public API is a compatibility contract for the 2.x line. Removals, renames, or any change to…

24k3mo agoDiscuss

NirDiamantAGENTS.md

GenAI_Agents

NirDiamant/GenAI_Agents/AGENTS.md

Guidance for AI coding agents working in this repository. Humans are welcome to read it too; it is plain Markdown and GitHub renders it. **GenAI_Agents* is a community-driven collection of…

24k16d agoDiscuss

nocobaseAGENTS.md

nocobase

nocobase/nocobase/AGENTS.md

This file holds the team-shared rules for AI coding agents working in this repository. It is the single source of truth — CLAUDE.md is a one-line bridge (@AGENTS.md) so Claude…

24k2y agoDiscuss

CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.