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 42Worked for most · soon

10k+ stars

NanmiCoderAGENTS.md

cc-haha

NanmiCoder/cc-haha/.github/AGENTS.md

These rules apply to .github/ changes in addition to the root instructions.

15k4d agoDiscuss

NanmiCoderAGENTS.md

These rules apply to the public landing page and documentation experience under site/. scripts/generate-docs-manifest.mjs scans docs/, then emits three things into src/generated/ (gitignored): Routes come from file paths (docs/start/install.md → /start/install). Renaming a file renames its URL, so add the old path to both LEGACY_ROUTES in src/content/docs.js and legacyRoutes in scripts/prepare-static-output.mjs. Sidebar grouping comes from the sections array in the generator — register any new top-level docs/ directory there or it sorts last with a bare directory name. Order inside…

15k4d agoDiscuss

NanmiCoderAGENTS.md

cc-haha / src

NanmiCoder/cc-haha/src/AGENTS.md

These rules apply to src/ changes in addition to the root instructions.

15k4d agoDiscuss

NVIDIAAGENTS.md

TensorRT-LLM / agent-flow

NVIDIA/TensorRT-LLM/agent-flow/AGENTS.md

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

15k46d agoDiscuss

NVIDIAAGENTS.md

TensorRT-LLM

NVIDIA/TensorRT-LLM/AGENTS.md

TensorRT-LLM: open-source library for optimized LLM inference on NVIDIA GPUs. Python and C++ codebase with a PyTorch execution path. If a CLAUDE.local.md file exists alongside this file, read and respect…

15k46d agoDiscuss

NVIDIAAGENTS.md

TensorRT-LLM

NVIDIA/TensorRT-LLM/.codex/AGENTS.md

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

15k46d agoDiscuss

NVIDIAAGENTS.md

TensorRT-LLM / kv_cache_manager_v2

NVIDIA/TensorRT-LLM/cpp/tensorrt_llm/batch_manager/kv_cache_manager_v2/AGENTS.md

This directory contains the C++ implementation of KVCacheManagerV2: allocation, prefix reuse, eviction, GPU/host/disk movement, page locking, and KV-cache event generation. Python accesses it through the nanobind bindings in cpp/tensorrtllm/nanobind/batchmanager/kvCacheManagerV2.cpp. This…

15k46d agoDiscuss

NVIDIAAGENTS.md

TensorRT-LLM / kv_cache_manager_v2

NVIDIA/TensorRT-LLM/tensorrt_llm/runtime/kv_cache_manager_v2/AGENTS.md

This file provides guidance to coding agents when working with code in this directory. KVCacheManagerV2 is the KV cache management subsystem for TensorRT-LLM. It manages GPU/host/disk memory for key-value caches…

15k46d agoDiscuss

NVIDIAAGENTS.md

TensorRT-LLM / tests

NVIDIA/TensorRT-LLM/tests/AGENTS.md

Scope: this directory and everything under it. Supplements the repo-root AGENTS.md. This is a reminder for whoever adds a test, not a hard gate. Not every test runs in CI…

15k46d agoDiscuss

NVIDIAAGENTS.md

TensorRT-LLM / visual_gen

NVIDIA/TensorRT-LLM/tests/integration/defs/visual_gen/AGENTS.md

Scope: this directory (tests/integration/defs/visual_gen/). Supplements the repo-root AGENTS.md. A VisualGen test that cannot run because a resource CI is expected to provide is missing must fail loudly, not pytest.skip —…

15k46d agoDiscuss

NVIDIAAGENTS.md

TensorRT-LLM / visual_gen

NVIDIA/TensorRT-LLM/tests/unittest/_torch/visual_gen/AGENTS.md

Scope: this directory and everything under it (tests/unittest/torch/visualgen/, including multigpu/, kernels/, sparseattention/). Supplements the repo-root AGENTS.md. A VisualGen test that cannot run because a resource CI is expected to provide…

15k46d agoDiscuss

superset-shAGENTS.md

superset

superset-sh/superset/AGENTS.md

Superset is an agent-first development platform, with an Electron desktop IDE, Next.js web apps, and an Expo mobile app as the main customer-facing surfaces. It's a Turborepo monorepo, deployed apps…

15k28d agoDiscuss

palmier-ioAGENTS.md

palmier-pro

palmier-io/palmier-pro/AGENTS.md

AI-native macOS video editor. Swift 6.2, SwiftUI + AppKit, AVFoundation. macOS 26 only, arm64 only. Non-sandboxed Developer ID app. Use swift build --traits BundledSpeech for changes that touch MLX, speech…

14k56d agoDiscuss

NevaMind-AIAGENTS.md

memU

NevaMind-AI/memU/AGENTS.md

Operational guide for AI coding agents working in this repository. Ship small, verified feature and bugfix changes while preserving memU's current architecture. Core invariants: Read the relevant implementation and nearby…

14k9mo agoDiscuss

MicrosoftAGENTS.md

agent-framework / dotnet

microsoft/agent-framework/dotnet/AGENTS.md

Instructions for AI coding agents working in the .NET codebase. See ./.github/skills/build-and-test/SKILL.md for detailed instructions on building, testing, and linting projects. See ./.github/skills/project-structure/SKILL.md for an overview of the project structure. See ./.github/skills/pull-requests/SKILL.md for guidance on writing PR descriptions and handling/resolving PR review comments. The framework integrates with Microsoft.Extensions.AI and Microsoft.Extensions.AI.Abstractions (external NuGet packages) using types like IChatClient, FunctionInvokingChatClient, AITool, AIFunction, ChatMessage, and AIContent. When developing or reviewing code, verify adherence to these key design principles: Samples (in ./samples/ folder) should…

14k8mo agoDiscuss

MicrosoftAGENTS.md

agent-framework / samples

microsoft/agent-framework/dotnet/samples/AGENTS.md

This file documents the structure and conventions of the .NET samples so that agents (AI or human) can maintain them without rediscovering decisions. 1. Progressive complexity: Sections 01→05 build from "hello world" to production. Within 01-get-started, projects are numbered 01–05 and each step adds exactly one concept.

14k8mo agoDiscuss

MicrosoftAGENTS.md

agent-framework / python

microsoft/agent-framework/python/AGENTS.md

Instructions for AI coding agents working in the Python codebase. Key Documentation: - DEVSETUP.md - Development environment setup and available poe tasks - CODINGSTANDARD.md - Coding standards, docstring format, and performance guidelines - samples/SAMPLE_GUIDELINES.md - Sample structure and guidelines - Python function-calling loop specification - Required behavior, scenario-to-test mapping, coverage gaps, and extra validation for function-loop changes Agent Skills (.github/skills/) — detailed, task-specific instructions loaded on demand: - python-development — coding standards, type annotations, docstrings, logging, performance - python-testing —…

14k8mo agoDiscuss

MicrosoftAGENTS.md

agent-framework / a2a

microsoft/agent-framework/python/packages/a2a/AGENTS.md

Agent-to-Agent (A2A) protocol support for inter-agent communication.

14k8mo agoDiscuss

MicrosoftAGENTS.md

agent-framework / ag-ui

microsoft/agent-framework/python/packages/ag-ui/AGENTS.md

AG-UI protocol integration for building agent UIs with the AG-UI standard. - AgentFrameworkAgent - Wraps agents for AG-UI compatibility - AgentFrameworkWorkflow - Wraps native Workflow objects, or accepts workflowfactory(threadid) for thread-scoped workflow instances without subclassing - AGUIChatClient - Chat client that speaks AG-UI protocol - AGUIHttpService - HTTP service for AG-UI endpoints - **agentframeworkmessagestoaguihosthistory()* - Converts persisted Agent Framework messages to bounded AG-UI Host history while retaining MCP widget payloads and model replay metadata - *AGUIEventConverter* - Converts between Agent…

14k8mo agoDiscuss

MicrosoftAGENTS.md

agent-framework / anthropic

microsoft/agent-framework/python/packages/anthropic/AGENTS.md

Integration with Anthropic's Claude API.

14k8mo 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.