PydanticAGENTS.mdpydantic-ai / toolsets
pydantic/pydantic-ai/pydantic_ai_slim/pydantic_ai/toolsets/AGENTS.md
Toolsets are reusable tool collections with lifecycle, instructions, and execution boundaries.
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 26Worked for most · soon
PydanticAGENTS.mdPydanticAGENTS.mdpydantic-ai / ui
pydantic/pydantic-ai/pydantic_ai_slim/pydantic_ai/ui/AGENTS.md
Since 3971 we decided to introduce the policy of sticking to the lower (existing) version requirement. In short, this means: - version requirement bumps are disallowed - new functionality should be gated behind version checks (including imports) - older versions don't error out when they encounter new functionality, but instead skip it The inbound half of that last rule lives in agui/forward_compat.py: AG-UI's Message and InputContent are discriminated unions, so a role or type added after the installed version is…
PydanticAGENTS.mdpydantic-ai / pydantic_ai_harness
pydantic/pydantic-ai/src/pydantic_ai_harness/AGENTS.md
pydantic-ai-harness is the first-party capability library for Pydantic AI. Pydantic AI core owns the primitive runtime: agent loop semantics, normalized messages, model/provider/profile behavior, tool execution semantics, durable execution primitives, and generic capability hooks. Harness owns optional, batteries-included compositions built from those primitives: coding-agent tools, guardrails, memory, context management, repo tools, verification loops, skills, planning, sub-agents, and other reusable agent behaviors. When a change needs new core semantics, stop and propose the Pydantic AI core change instead of reimplementing core behavior…
PydanticAGENTS.mdpydantic-ai / pydantic_clai2
pydantic/pydantic-ai/src/pydantic_clai2/AGENTS.md
Read this before touching pydantic-clai2/. The repository-level AGENTS.md still applies (no em-dashes, no Any, pyright strict, keyword-only arguments, 100% branch coverage). This file adds what is specific to the terminal shell. A thin terminal around any Pydantic AI agent. It reads a prompt, runs the agent, streams the answer, and repeats. Everything beyond that is a plugin, including the default coding tools. The three layers, and who owns what: If a change needs the agent loop to behave differently, propose…
PydanticAGENTS.mdpydantic-ai / tests
pydantic/pydantic-ai/tests/AGENTS.md
The async backend defaults to asyncio. Use uv run pytest <test-path> --anyio-backend=trio --record-mode=none to run selected portable tests on Trio without duplicating the default suite. During the Trio migration, run affected concurrency tests once per backend. Keep broad Trio runs manual or periodic; do not add a second backend to every ordinary CI matrix. The selector does not imply that every test or integration already supports Trio. VCR + public-API tests are the default. We test through the public API…
PydanticAGENTS.mdpydantic-ai / benchmarks
pydantic/pydantic-ai/tests/benchmarks/AGENTS.md
No summary in the file. Open it to read it.
AstralAGENTS.mdty
astral-sh/ty/AGENTS.md
Parts of .github/workflows/release.yml are generated by cargo-dist from dist-workspace.toml. Before editing the release workflow, check whether the relevant section is generated. Prefer changing dist-workspace.toml or the referenced reusable workflow instead of editing generated YAML. After modifying cargo-dist configuration, regenerate the workflow with the cargo-dist version pinned in dist-workspace.toml and inspect the resulting diff to ensure the change will survive future regenerations. For reviews of this repository's GitHub automation, CI, and release process, use the GitHub repository threat model. The ruff…
GoogleAGENTS.mdgvisor
google/gvisor/AGENTS.md
You are an expert Systems Engineer specializing in Linux Kernel internals, the Linux ABI, and systems programming in Go. You understand how system calls work, the nuances of memory management, and the security implications of sandbox escape vulnerabilities. gVisor is a user-space kernel, written in Go, that implements a substantial portion of the Linux system surface. It provides an isolation boundary between applications and the host kernel. - Sentry: The heart of gVisor; it acts as the "kernel" running the…
GoogleAGENTS.mdgvisor / gnome-mcp
google/gvisor/images/systemd-user/gnome-mcp/AGENTS.md
You drive a GNOME desktop through the desktop__* tools. There is nothing else to work with: no shell on that machine, no filesystem access, no APIs. If you want to know something about the desktop, you have to look at it and click on it, the same way a person sitting in front of it would. Every action tool returns the screen it produced. You do not need to ask for a screenshot after acting — you already have one.…
Hugging FaceAGENTS.mdtrl
huggingface/trl/.ai/AGENTS.md
The repository is separated into main code and experimental code. Small non-invasive improvements that make experimental code more consistent with the main codebase are encouraged, but avoid large refactors. If a PR implements a method, algorithm, or training approach from a research paper, it must also add a corresponding subsection to paper_index.md. When reviewing such PRs, ensure that paper_index.md was updated. Trainers in this repository are self-contained by design. Shared logic (generation, reward computation, metric logging, weight syncing, etc.) is…
VercelAGENTS.mdjson-render
vercel-labs/json-render/AGENTS.md
Instructions for AI coding agents working with this codebase. Always check the latest version before installing a package. Before adding or updating any dependency, verify the current latest version on npm: Or check multiple packages at once: This ensures we don't install outdated versions that may have incompatible types or missing features. When using the Vercel AI SDK (ai package) with AI Gateway, pass the model as a plain string identifier -- do not import a provider constructor: This requires…
LangChainAGENTS.mdlangchainjs
langchain-ai/langchainjs/AGENTS.md
This document provides guidance for AI coding agents working with the LangChain.js codebase. When Corridor's analyzePlan tool is available, create a plan and use the tool to analyze it before generating or modifying code. Apply the resulting security guidance before writing code. LangChain.js is a TypeScript framework for building LLM-powered applications. It provides standard interfaces for agents, models, embeddings, vector stores, and more, enabling developers to chain together interoperable components and third-party integrations. This is a monorepo managed with pnpm…
NVIDIAAGENTS.mdMegatron-LM
NVIDIA/Megatron-LM/AGENTS.md
The skills/ directory contains structured guides for common tasks (running tests, building containers, managing dependencies, submitting SLURM jobs, etc.). Always read the relevant SKILL.md before starting any task it covers…
NVIDIAAGENTS.mdMegatron-LM / hybrid
NVIDIA/Megatron-LM/megatron/core/models/hybrid/AGENTS.md
For new or modified code, keep files directly under this directory generic and independent of any particular layer implementation. Put layer-specific behavior in layers/ or with the owning layer's code.…
Google CloudAGENTS.mdgenerative-ai / ge-demo-generator
GoogleCloudPlatform/generative-ai/search/gemini-enterprise/ge-demo-generator/AGENTS.md
Purpose: Project-specific knowledge for AI coding agents (Antigravity, Cursor, Copilot, etc.) and humans working on this sample. Per-demo variation is passed at run time, never baked into the Python: Edit directly. No escaping rules apply. Validate with: Feature-dependent code is gated at run time, not generation time: Keep that pattern — do not reintroduce generation-time code selection. generateSetupScript still emits bash (BigQuery/Firestore provisioning, Dockerfile assembly, deployment). Inside those JS template literals: - Emit a literal bash ${VAR} as \${VAR}; a…
Google CloudAGENTS.mdgenerative-ai / group-licensing
GoogleCloudPlatform/generative-ai/search/gemini-enterprise/group-licensing/AGENTS.md
[!IMPORTANT] Before making any code changes, architectural decisions, or refactoring in this codebase, any skill, agent, or subagent MUST first read the service Technical Design Document (TDD) located at docs/TDD.md (in the docs/ subdirectory). This document contains the definitive architectural requirements, data flows, and design rationale for the service. No linter config is present; use go vet ./... for static checks. Strict Ports and Adapters (Hexagonal Architecture). The layers must not be mixed: Every adapter declares a compile-time interface satisfaction…
MicrosoftAGENTS.mdmcp-for-beginners
microsoft/mcp-for-beginners/AGENTS.md
MCP for Beginners is an open-source educational curriculum for learning the Model Context Protocol (MCP) - a standardized framework for interactions between AI models and client applications. This repository provides comprehensive learning materials with hands-on code examples across multiple programming languages. This is a documentation-focused repository. Most setup occurs within individual sample projects and labs. Sample projects are located in: - 03-GettingStarted/samples/ - Language-specific examples - 03-GettingStarted/01-first-server/solution/ - First server implementations - 03-GettingStarted/02-client/solution/ - Client implementations - 11-MCPServerHandsOnLabs/ - Comprehensive…
MicrosoftAGENTS.mdmcp-for-beginners / ar
microsoft/mcp-for-beginners/translations/ar/AGENTS.md
MCP للمبتدئين هو منهج تعليمي مفتوح المصدر لتعلم بروتوكول سياق النموذج (MCP) - إطار عمل معياري للتفاعلات بين نماذج الذكاء الاصطناعي وتطبيقات العملاء. يوفر هذا المستودع مواد تعليمية شاملة مع أمثلة تعليمية عملية عبر لغات برمجة متعددة. هذا المستودع موجه للوثائق. يتم معظم الإعداد داخل المشاريع النموذجية والمعامل الفردية. تقع المشاريع النموذجية في: - 03-GettingStarted/samples/ - أمثلة خاصة بكل لغة - 03-GettingStarted/01-first-server/solution/ - تنفيذات الخادم الأولى - 03-GettingStarted/02-client/solution/ - تنفيذات العميل - 11-MCPServerHandsOnLabs/ - معامل تكامل قواعد بيانات شاملة يحتوي…
MicrosoftAGENTS.mdmcp-for-beginners / bg
microsoft/mcp-for-beginners/translations/bg/AGENTS.md
MCP за начинаещи е отворен образователен курс за изучаване на Model Context Protocol (MCP) - стандартизиран рамков протокол за взаимодействия между AI модели и клиентски приложения. Това хранилище предоставя пълни учебни материали с практическо кодиране на няколко програмни езика. Това е подредено хранилище, фокусирано върху документацията. Повечето настройки се извършват в отделни примерни проекти и лаборатории. Примерните проекти се намират в: - 03-GettingStarted/samples/ - Езиково специфични примери - 03-GettingStarted/01-first-server/solution/ - Първи имплементации на сървър - 03-GettingStarted/02-client/solution/ - Клиентски имплементации -…
MicrosoftAGENTS.mdmcp-for-beginners / bn
microsoft/mcp-for-beginners/translations/bn/AGENTS.md
শুরুকারীদের জন্য MCP হল মডেল কন্টেক্সট প্রোটোকল (MCP) শেখার জন্য একটি ওপেন-সোর্স শিক্ষামূলক পাঠক্রম - যা AI মডেল এবং ক্লায়েন্ট অ্যাপ্লিকেশনের মধ্যে যোগাযোগের জন্য একটি মানসম্মত কাঠামো। এই রিপোজিটরিটি বিভিন্ন প্রোগ্রামিং ভাষায় হাতে-কলমে কোড উদাহরণের সাথে ব্যাপক শিক্ষামূলক উপকরণ সরবরাহ করে। এটি একটি ডকুমেন্টেশন-কেন্দ্রিক রিপোজিটরি। বেশিরভাগ সেটআপ আলাদা আলাদা নমুনা প্রকল্প এবং ল্যাবসের মধ্যে হয়। নমুনা প্রকল্পগুলি অবস্থিত: - 03-GettingStarted/samples/ - ভাষা-বিশেষ উদাহরণ - 03-GettingStarted/01-first-server/solution/ - প্রথম সার্ভার বাস্তবায়ন - 03-GettingStarted/02-client/solution/ - ক্লায়েন্ট বাস্তবায়ন - 11-MCPServerHandsOnLabs/ - পূর্ণাঙ্গ ডেটাবেস একীকরণ…
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.