How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
lobehubAGENTS.mdlobehub/lobehub/AGENTS.md
Guidelines for using AI coding agents in this opensource LobeHub repository. AGENTS.md owns repository-wide architecture and workflow. Keep detailed implementation rules in skills so they have one source of truth.
stablyaiAGENTS.mdstablyai/orca/AGENTS.md
All UI work — layout, color, typography, spacing, component selection, UX behavior — must follow docs/STYLEGUIDE.md. Most of it is linted: pnpm run check:code-quality:changed fails on new restyles of a components/ui/ primitive, raw palette colors, and computed className strings; pnpm lint fails on any class Tailwind cannot generate. See the Enforcement section of the style guide before suppressing either. Use the tokens defined in src/renderer/src/assets/main.css (the canonical source) and the shadcn primitives in src/renderer/src/components/ui/. Don't invent new color values, font…
stablyaiAGENTS.mdstablyai/orca/tests/AGENTS.md
Tests and agent-driven app launches share the developer's machine. They may use it; they must never take the foreground — no window raised over the editor, no focus stolen, no Dock tile churn. src/main/window/foreground-activation-policy.ts enforces this in the main process. It is on whenever ORCAE2EHEADLESS=1, ORCAE2EHEADFUL=1, or ORCABACKGROUNDLAUNCH=1: - headless / explicit background → the window never reaches the screen (Playwright drives it via CDP) - headful without explicit background → showInactive(), no app.focus({ steal: true }), no moveTop()/always-on-top reinforcement…
ElasticAGENTS.mdelastic/elasticsearch/AGENTS.md
Stateless Elasticsearch is a distribution where shard data is stored in an object store (e.g., S3, GCS, Azure) rather than local disk. Nodes carry no durable local state. The cluster…
ElasticAGENTS.mdelastic/elasticsearch/benchmarks/AGENTS.md
Run from the benchmarks/ directory using the run task with --args. Always use the fully-qualified class name including package to avoid ambiguity. Always pipe through tee /tmp/bench/<descriptivename> using a filename…
ElasticAGENTS.mdelastic/elasticsearch/docs/AGENTS.md
Always run docs-builder from the root of the checkout, not from a subdirectory. Running from a subdirectory will only validate that subdirectory's links and may silently miss errors in cross-document…
OpenAIAGENTS.mdopenai/openai-cookbook/AGENTS.md
The cookbook is organized around runnable examples and reference articles for OpenAI APIs. Place notebooks and Python scripts under examples/<topic>/, grouping related assets inside topic subfolders (for example, examples/agents_sdk/). Narrative guides and long-form docs live in articles/, and shared diagrams or screenshots belong in images/. Update registry.yaml whenever you add content so it appears on cookbook.openai.com, and add new author metadata in authors.yaml if you want custom attribution. Keep large datasets outside the repo; instead, document how to fetch them…
OpenAIAGENTS.mdopenai/openai-cookbook/examples/agents_sdk/sandboxed-code-migration/migration_agent/AGENTS.md
You are migrating the mounted repo under repo/. - Migrate the repo according to repo/MIGRATION.md. - Preserve the public function signatures and behavior. - Run the baseline test command before editing. - Edit the app code and its tests. - Run the check command named in repo/MIGRATION.md after editing. - Run the final test command named in repo/MIGRATION.md after editing. - Return structured output that includes the exact commands, pass/fail summaries, changed files, a Markdown migration report, and the patch…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/AGENTS.md
This repository contains "AI Agents for Beginners" - a comprehensive educational course teaching everything needed to build AI Agents. The course consists of 18 lessons (numbered 00-18) covering fundamentals, design patterns, frameworks, production deployment, local/on-device agents, and security of AI agents. Key Technologies: - Python 3.12+ - Jupyter Notebooks for interactive learning - AI Frameworks: Microsoft Agent Framework (MAF) - Azure AI Services: Microsoft Foundry, Microsoft Foundry Agent Service V2 Architecture: - Lesson-based structure (00-18 directories) - Each lesson contains:…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/ar/AGENTS.md
يحتوي هذا المستودع على "وكلاء الذكاء الاصطناعي للمبتدئين" - دورة تعليمية شاملة تعلم كل ما يلزم لبناء وكلاء الذكاء الاصطناعي. تتألف الدورة من 18 درسًا (مرقمة من 00 إلى 18) تغطي الأساسيات، أنماط التصميم، الأُطر، النشر في الإنتاج، الوكلاء المحليين/على الجهاز، وأمان وكلاء الذكاء الاصطناعي. التقنيات الرئيسية: - بايثون 3.12+ - دفاتر جوبيتر للتعلم التفاعلي - أُطر الذكاء الاصطناعي: إطار عمل الوكيل من مايكروسوفت (MAF) - خدمات الذكاء الاصطناعي في أزور: Microsoft Foundry، خدمة وكلاء Microsoft Foundry V2 البنية: -…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/bg/AGENTS.md
Това хранилище съдържа "AI агенти за начинаещи" - изчерпателен образователен курс, който учи всичко необходимо за изграждане на AI агенти. Курсът се състои от 18 урока (номерирани от 00 до 18), покриващи основи, дизайн патърни, рамки, внедряване в продукция, локални/устройствени агенти и сигурността на AI агентите. Ключови технологии: - Python 3.12+ - Jupyter тетрадки за интерактивно обучение - AI рамки: Microsoft Agent Framework (MAF) - Azure AI услуги: Microsoft Foundry, Microsoft Foundry Agent Service V2 Архитектура: - Структура базирана на…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/bn/AGENTS.md
এই রিপোজিটরিতে রয়েছে "শুরুর জন্য AI এজেন্টস" - একটি বিস্তৃত শিক্ষামূলক কোর্স যা AI এজেন্ট তৈরির জন্য প্রয়োজনীয় সবকিছু শেখায়। কোর্সটিতে ১৮টি ধাপ (নম্বর ০০-১৮) রয়েছে যা অন্তর্ভুক্ত করে মৌলিক বিষয়াবলী, ডিজাইন প্যাটার্ন, ফ্রেমওয়ার্ক, উৎপাদন স্থাপনা, স্থানীয়/ডিভাইস-ভিত্তিক এজেন্টস, এবং AI এজেন্টসের নিরাপত্তা। মূল প্রযুক্তিগুলি: - পাইথন ৩.১২+ - ইন্টারেক্টিভ শেখার জন্য জুপিটার নোটবুক - AI ফ্রেমওয়ার্ক: মাইক্রোসফট এজেন্ট ফ্রেমওয়ার্ক (MAF) - আজুর AI সার্ভিস: মাইক্রোসফট ফাউন্ড্রি, মাইক্রোসফট ফাউন্ড্রি এজেন্ট সার্ভিস V2 স্থাপত্য: - পাঠ ভিত্তিক কাঠামো (০০-১৫+ ডিরেক্টরিজ) - প্রতিটি…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/cs/AGENTS.md
Toto úložiště obsahuje „AI Agentů pro začátečníky“ - komplexní vzdělávací kurz, který učí vše potřebné k vytvoření AI agentů. Kurz se skládá z 18 lekcí (číslovaných 00-18), pokrývajících základy, designové vzory, frameworky, nasazení do produkce, lokální/agenty na zařízení a bezpečnost AI agentů. Klíčové technologie: - Python 3.12+ - Jupyter Notebooks pro interaktivní učení - AI Frameworky: Microsoft Agent Framework (MAF) - Azure AI služby: Microsoft Foundry, Microsoft Foundry Agent Service V2 Architektura: - Struktura založená na lekcích (adresáře 00-15+) -…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/da/AGENTS.md
Dette repository indeholder "AI-agenter for begyndere" - et omfattende undervisningsforløb, der lærer alt, hvad der er nødvendigt for at bygge AI-agenter. Kurset består af 18 lektioner (nummereret 00-18), der dækker grundlæggende principper, designmønstre, frameworks, produktion-udrulning, lokale/enhedsbårne agenter og sikkerhed for AI-agenter. Nøgleteknologier: - Python 3.12+ - Jupyter Notebooks til interaktiv læring - AI Frameworks: Microsoft Agent Framework (MAF) - Azure AI Services: Microsoft Foundry, Microsoft Foundry Agent Service V2 Arkitektur: - Lektion-baseret struktur (00-15+ mapper) - Hver lektion indeholder: README-dokumentation,…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/de/AGENTS.md
Dieses Repository enthält "KI-Agenten für Anfänger" - einen umfassenden Bildungskurs, der alles vermittelt, was zum Erstellen von KI-Agenten benötigt wird. Der Kurs besteht aus 18 Lektionen (nummeriert 00-18) und behandelt Grundlagen, Designmuster, Frameworks, Produktionseinsatz, lokale/On-Device-Agenten und Sicherheit von KI-Agenten. Wichtige Technologien: - Python 3.12+ - Jupyter-Notebooks für interaktives Lernen - KI-Frameworks: Microsoft Agent Framework (MAF) - Azure KI-Dienste: Microsoft Foundry, Microsoft Foundry Agent Service V2 Architektur: - Lektionen-basierte Struktur (00-15+ Verzeichnisse) - Jede Lektion enthält: README-Dokumentation, Codebeispiele (Jupyter-Notebooks) und Bilder…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/el/AGENTS.md
Αυτό το αποθετήριο περιέχει "Πρακτικοί Πράκτορες Τεχνητής Νοημοσύνης για Αρχάριους" - ένα ολοκληρωμένο εκπαιδευτικό μάθημα που διδάσκει όλα όσα χρειάζονται για την κατασκευή Πρακτικών Πρακτόρων Τεχνητής Νοημοσύνης. Το μάθημα αποτελείται από 18 μαθήματα (αριθμημένα 00-18) που καλύπτουν βασικές έννοιες, πρότυπα σχεδίασης, πλαίσια, ανάπτυξη σε παραγωγή, πράκτορες τοπικά ή στη συσκευή, και ασφάλεια των πρακτόρων ΤΝ. Κύριες Τεχνολογίες: - Python 3.12+ - Jupyter Notebooks για διαδραστική μάθηση - Πλαίσια Τεχνητής Νοημοσύνης: Microsoft Agent Framework (MAF) - Υπηρεσίες Azure AI: Microsoft Foundry,…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/en/AGENTS.md
This repository contains "AI Agents for Beginners" - a comprehensive educational course teaching everything needed to build AI Agents. The course consists of 18 lessons (numbered 00-18) covering fundamentals, design patterns, frameworks, production deployment, local/on-device agents, and security of AI agents. Key Technologies: - Python 3.12+ - Jupyter Notebooks for interactive learning - AI Frameworks: Microsoft Agent Framework (MAF) - Azure AI Services: Microsoft Foundry, Microsoft Foundry Agent Service V2 Architecture: - Lesson-based structure (00-15+ directories) - Each lesson contains:…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/es/AGENTS.md
Este repositorio contiene "Agentes de IA para Principiantes" - un curso educativo integral que enseña todo lo necesario para construir Agentes de IA. El curso consta de 18 lecciones (numeradas 00-18) que cubren fundamentos, patrones de diseño, frameworks, despliegue en producción, agentes locales/en dispositivo y seguridad de los agentes de IA. Tecnologías Clave: - Python 3.12+ - Jupyter Notebooks para aprendizaje interactivo - Frameworks de IA: Microsoft Agent Framework (MAF) - Servicios de IA de Azure: Microsoft Foundry, Microsoft Foundry…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/et/AGENTS.md
See hoidla sisaldab "Tehisintellekti agendid algajatele" - põhjalikku õppeprogrammi, mis õpetab kõike, mida on vaja tehisintellekti agentide loomiseks. Kursus koosneb 18 õppetükist (nummerdatud 00–18), mis hõlmavad põhialuseid, disainimustreid, raamistikke, tootmispaigaldust, kohalikku/seadmesiseset agenti ja tehisintellekti agentide turvalisust. Peamised tehnoloogiad: - Python 3.12+ - Interaktiivseks õppimiseks Jupyter märkmed - Tehisintellekti raamistikud: Microsoft Agent Framework (MAF) - Azure'i tehisintellekti teenused: Microsoft Foundry, Microsoft Foundry Agent Service V2 Arhitektuur: - Õppetükkide põhine struktuur (00-15+ kataloogid) - Igas õppetükis on: README dokumentatsioon, koodi näited (Jupyter…
MicrosoftAGENTS.mdmicrosoft/ai-agents-for-beginners/translations/fa/AGENTS.md
این مخزن شامل "عاملهای هوش مصنوعی برای مبتدیان" است - یک دوره آموزشی جامع که همه موارد لازم برای ساخت عاملهای هوش مصنوعی را آموزش میدهد. این دوره شامل ۱۸ درس (شمارهگذاری شده از ۰۰ تا ۱۸) است که اصول پایه، الگوهای طراحی، چارچوبها، استقرار در تولید، عاملهای محلی/روی دستگاه، و امنیت عاملهای هوش مصنوعی را پوشش میدهد. فناوریهای کلیدی: - پایتون ۳.۱۲ به بالا - دفترچههای Jupyter برای یادگیری تعاملی - چارچوبهای هوش مصنوعی: چارچوب عامل مایکروسافت (MAF) -…
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.
