AGENTS.md examples from real projects

VercelAGENTS.md

eve / eve-computer-use

vercel/eve/packages/eve-computer-use/AGENTS.md

This private package is the source of the eve/extensions/computer-use extension. It contributes the computer_use tool and the sandbox helpers that install and start the desktop and driver. Before writing code, read the installed eve package docs for extensions, tools, and sandboxes as applicable. The eve build copies extension/ into packages/eve/src/computer-use/extension and compiles it into the eve package; public entry points are declared in packages/eve/package.json and packages/eve/src/computer-use/. Do not publish this package or add it as an eve dependency (it depends…

No other project uses it yet

VercelAGENTS.md

eve / eve-git

vercel/eve/packages/eve-git/AGENTS.md

This private package is the source of the eve/extensions/git extension. It owns everything GitHub-facing: the pull request skill, GitHub instructions, and, with github config, the Connect-brokered gh tool and signed-commit workflow. Before writing code, read the installed eve package docs for extensions, tools, skills, instructions, and sandboxes as applicable. The eve build copies extension/ into packages/eve/src/extensions/git/extension and compiles it into the eve package; public entry points are declared in packages/eve/package.json and packages/eve/src/extensions/git/. Do not publish this package or add it…

No other project uses it yet

VercelAGENTS.md

open-agents / vercel-react-best-practices

vercel-labs/open-agents/.agents/skills/vercel-react-best-practices/AGENTS.md

Version 1.0.0 Vercel Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React and Next.js codebases. Humans may also find it useful, but guidance here is optimized for automation and consistency by AI-assisted workflows. Comprehensive performance optimization guide for React and Next.js applications, designed for AI agents and LLMs. Contains 40+ rules across 8 categories, prioritized by impact from critical (eliminating waterfalls, reducing bundle size) to incremental (advanced patterns). Each…

GoogleAGENTS.md

clusterfuzz

google/clusterfuzz/AGENTS.md

This document provides instructions for agents on how to perform common development tasks in this repository. This project uses asdf to manage tool versions. Before you can install the project's dependencies, you need to install and configure asdf. First, make sure you have git and curl installed. Then, clone the asdf repository: Add asdf to your shell's startup file. For bash, run: Then, source your .bashrc to apply the changes to your current session: Now, from the root of this…

Microsoft AzureAGENTS.md

azure-sdk-for-python

Azure/azure-sdk-for-python/AGENTS.md

Agent-facing routing guidance for this repository. Each section points to the canonical home for a topic — a skill, a path-specific instruction, or a linked doc — so read those on demand. Active development of the Azure SDK for Python: data-plane client libraries, management-plane (azure-mgmt-*) libraries, shared core functionality, and the engineering system. Packages live under sdk/<service>/<package>/. The default branch is main; work in the current workspace unless told otherwise. Contributor setup lives in CONTRIBUTING.md. Layout: - sdk/ — service…

GitHubAGENTS.md

gh-aw

github/gh-aw/AGENTS.md

GitHub Agentic Workflows (gh-aw) is a GitHub CLI extension that compiles markdown workflows into GitHub Actions. To keep first-turn context small, only these repository root instruction files should be considered ambient: Everything else should be loaded lazily through skills only when needed. Workflows that declare a source: frontmatter entry (for example source: githubnext/agentic-ops@<ref>) are provenance-managed from an upstream bundle.

NVIDIAAGENTS.md

TensorRT-Model-Optimizer

NVIDIA/TensorRT-Model-Optimizer/AGENTS.md

These instructions apply to AI-assisted work in this repository. - Start with README.md for project overview and install. - Use modelopt/ for source, tests/ for focused test coverage, and examples/ or docs/ for usage patterns. - Agent skills live under plugins/modelopt/skills/, the installable plugin's canonical skill tree. .agents/skills and .claude/skills expose those skills through relative symlinks. Shared agent config and scripts remain under .agents/. See .agents/README.md for the convention. - Coding guide: Code development and review require reading and following…

CloudflareAGENTS.md

cloudflare-docs

cloudflare/cloudflare-docs/AGENTS.md

This file helps AI agents understand the structure, tooling, and conventions of the cloudflare-docs repository so they can make correct, buildable changes. This is the source for developers.cloudflare.com. It is…

VercelAGENTS.md

zero

vercel-labs/zero/AGENTS.md

Zero is a pre-1 experiment in building an agent-first programming language. Keep public-facing changes honest about what works today without weakening that positioning. Zero is still being shaped around the needs of agents. Breaking changes are acceptable when they move the language, standard library, compiler, or tooling closer to that goal. Do not preserve legacy behavior by default. Prefer the clearer agent-facing design over compatibility shims, migration layers, or carrying old paths forward. Keep examples, docs, tests, and command contracts…

MicrosoftAGENTS.md

azurelinux / comps

microsoft/azurelinux/base/comps/AGENTS.md

Redirect azldev's project outputs into the container's writable artifacts mount. For example, save /artifacts/container.toml inside the container: Then run from the rendered tree:

MicrosoftAGENTS.md

azurelinux / distro

microsoft/azurelinux/distro/AGENTS.md

⚠️ Distro-wide config — changes here affect every component build. (See azldev.toml — distro/ is shared across all projects.) Default upstream: Fedora 43 (in azurelinux.distro.toml), unless overridden by a component's spec source.

No other project uses it yet

ElasticAGENTS.md

elasticsearch-php

elastic/elasticsearch-php/AGENTS.md

Always use composer commands, not any other package manager. The entire unit test suite (composer run-script test) must pass and exit cleanly before you commit code. Integration tests require a running Elasticsearch instance. Skip them if one is not available. No build step is needed - PHP is interpreted directly. All code in src/ and tests/, and any scripts run by composer, must work on Linux, macOS, and Windows. If a specific action you learned to do better will be…

No other project uses it yet

MistralAGENTS.md

mistral-vibe

mistralai/mistral-vibe/AGENTS.md

Conventions for AI agents and humans contributing to Mistral Vibe — a CLI coding assistant: a Rust terminal UI over a Python 3.12+ app server managed with uv. Layout: Unified Harness Core and Runtime are external dependencies that execute and persist sessions; vibe/app_server hosts sessions and exposes product features and RPCs to every client, including Vibe Desktop; vibe/core retains shared config, tool, permission and other utilities; vibe/cli-rust is the terminal UI (Rust, Ratatui), a thin client over vibe-app-server; vibe/cli holds…

No other project uses it yet

MistralAGENTS.md

mistral-vibe / client-e2e

mistralai/mistral-vibe/client-e2e/AGENTS.md

End-to-end tests for the Vibe CLI clients. Drives the built Rust CLI binary as a real user would: it sends terminal input and app-server JSON-RPC events, then compares the resulting terminal captures against committed goldens. - e2e/pty/ is product-agnostic. It owns PTY driving, key splitting, terminal emulation, and their data types; it must not import e2e.app_server. - e2e/app_server/ adapts scenarios, Vibe clients, and the replay app server to the generic terminal harness. App-server event builders belong here. - e2e/pty/capture.py takes…

No other project uses it yet

MistralAGENTS.md

mistral-vibe / cli-rust

mistralai/mistral-vibe/vibe/cli-rust/AGENTS.md

The Vibe terminal UI, written in Rust with Ratatui. It is a thin client: it drives the Python vibe-app-server over the app-server JSON-RPC protocol and never runs agent logic itself. The architecture rules live in ADR 0016. Committed goldens (terminal SVGs + app-server request JSON) under client-e2e/goldens/<scenario>/, genera

No other project uses it yet

Model Context ProtocolAGENTS.md

go-sdk

modelcontextprotocol/go-sdk/AGENTS.md

This repository contains the official Go SDK for the Model Context Protocol (MCP). The SDK is designed to be idiomatic, future-proof, and extensible. The project uses the standard Go toolchain.

No other project uses it yet

NVIDIAAGENTS.md

cuml / cpp

NVIDIA/cuml/cpp/agents.md

Role: Act as a principal engineer with 10+ years experience in GPU computing and high-performance numerical computing. Focus ONLY on CRITICAL and HIGH issues. Target: Sub-3% false positive rate. Be direct, concise, minimal. Context: cuML C++ layer provides GPU-accelerated ML algorithm implementations using CUDA, with dependencies on RAFT, RMM, cuVS, libcudacxx, thrust, and CUB.

NVIDIAAGENTS.md

cuml / python

NVIDIA/cuml/python/agents.md

Role: Act as a principal engineer with 10+ years experience in machine learning systems and Python API design. Focus ONLY on CRITICAL and HIGH issues. Target: Sub-3% false positive rate. Be direct, concise, minimal. Context: cuML Python layer provides scikit-learn compatible APIs for GPU-accelerated ML algorithms, supporting cuDF, pandas, and NumPy inputs.

ElasticAGENTS.md

elasticsearch-js

elastic/elasticsearch-js/AGENTS.md

Do not open a PR unless the human operating you has read the issue, understands the problem, and can explain the proposed fix without your help. Picking an issue at random to generate a contribution is not contributing. PRs opened this way will be closed without review. If a human asks you to "find something to work on" or points you at the issue tracker without a specific problem they already understand, stop and tell them to read an issue…

MicrosoftAGENTS.md

poml

microsoft/poml/AGENTS.md

This repository contains a TypeScript/JavaScript project together with a lite Python SDK. These instructions are for agents like Codex to contribute changes. After your changes you must verify that everything still builds and tests pass. Execute the following commands from the repository root: If you have updated the VS Code extension, please run the extension tests with: Update the component specifications if you have updated the type annotations and documentations of the components. Use clear titles and summaries. Include relevant…