How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
CloudflareAGENTS.mdcloudflare/quiche/tokio-quiche/src/http3/driver/AGENTS.md
Async HTTP/3 driver bridging quiche::h3::Connection to Tokio tasks via channels. H3Driver<H: DriverHooks> is generic over sealed client/server hooks; users interact through H3Controller + typed event/command channels.
CloudflareAGENTS.mdcloudflare/quiche/tokio-quiche/src/quic/AGENTS.md
Async QUIC connection management. Splits socket into recv-half (one InboundPacketRouter task) and send-half (shared by many IoWorker tasks). Entrypoints: connect()/connectwithconfig() for clients, start_listener() for servers. raw submodule bypasses the router for manual packet injection.
ElasticAGENTS.mdelastic/beats/AGENTS.md
Elastic Beats is a Go monorepo containing lightweight data shippers for the Elastic Stack. The module path is github.com/elastic/beats/v7. Go version: see .go-version. The primary build tool is Mage (Go-based).…
VercelAGENTS.mdvercel-labs/portless/AGENTS.md
Use pnpm for all package management commands (not npm or yarn). Exception: End-user install instructions should use npm install -g (global) or npm install -D (project dev dependency) since npm is universal. Always check for the latest npm version when adding dependencies. Use pnpm add <package> (without version) to get the latest, or verify with npm view <package> version first. Do not use emojis anywhere in this repository (code, comments, output, docs). Never use -- as a dash in prose,…
corsairdevAGENTS.mdcorsairdev/corsair/AGENTS.md
Corsair is an open-source integration layer for agents (~70 plugin packages). - packages/<plugin>/ — one integration each (slack, gmail, …). Everything except corsair, cli, mcp, studio, ui, app is a…
krillinaiAGENTS.mdkrillinai/OpenCreator/AGENTS.md
No summary in the file. Open it to read it.
Untrivial-aiAGENTS.mdUntrivial-ai/agent-orchestrator/AGENTS.md
Operational guidance for coding agents working in this repository. Keep changes small, match the current rewrite architecture, and prefer the documented daemon/API boundaries over behavior from the old TypeScript implementation. From the repo root unless noted: Backend-specific checks: Frontend-specific checks: When showing or demoing frontend changes, run ao preview [url] from inside the session so the change renders in the desktop browser panel (the inspector rail's Browser tab); do not just describe it. For visual verification that needs the real…
NVIDIAAGENTS.mdNVIDIA/cosmos/cookbooks/cosmos3/nim/AGENTS.md
These instructions help customers deploy, call, and troubleshoot the Cosmos3 Certified NIM from this public documentation directory. For guided customer workflows, load .agents/skills/cosmos3-nim-user/SKILL.md. - Start by asking whether the customer…
BeehiveInnovationsAGENTS.mdBeehiveInnovations/pal-mcp-server/AGENTS.md
See requirements.txt and requirements-dev.txt Also read CLAUDE.md and CLAUDE.local.md if available. Run code quality checks: For example, this is how we run an individual / all tests:
MemTensorAGENTS.mdMemTensor/MemOS/AGENTS.md
Single source of truth for the project across AI runtimes. Claude Code, Codex, Cursor, Copilot, etc. all defer to this file. Runtime-specific adaptation belongs in each runtime's own file (Claude reads CLAUDE.md); do not mix it in here. MemOS / MemoryOS: a memory operating system for LLM agents. Python library plus a FastAPI service, providing multiple memory types (textual / tree / preference / skill / KV cache / LoRA parametric) plus scheduling, version management, and vector & graph storage.
cocoindex-ioAGENTS.mdcocoindex-io/cocoindex/AGENTS.md
Claude Code compatibility is kept through CLAUDE.md, which imports this file. This project uses uv for Python project management. CI enforces the full pre-commit hook suite from .pre-commit-config.yaml, which covers more than the commands above — notably regenerating the CLI docs (docs/src/content/docs/cli.mdx) whenever cli.py changes. Run it locally before pushing: After changing a core engine API (rust/core), run cargo check --workspace --all-targets to catch call sites in every workspace crate — both rust/py and the Rust SDK under rust/sdk/ call…
cocoindex-ioAGENTS.mdcocoindex-io/cocoindex/examples/AGENTS.md
Guidance for AI coding agents (Claude Code, Cursor, etc.) working in this examples/ directory. Most top-level Python subfolders are self-contained, runnable CocoIndex v1 apps; rust/ contains Rust ports with per-example READMEs. CocoIndex v1 is a fundamental redesign from v0. Without context, LLMs tend to hallucinate the v0 flow-builder DSL and deprecated decorators. Install the official skill first — it teaches the correct v1 API. Quickest portable path for Codex and other Agent Skills-compatible clients is the hosted skill: Or clone…
cobusgreylingAGENTS.mdcobusgreyling/loop-engineering/AGENTS.md
Conventions for humans and loops maintaining this repository. Front door map: docs/cli-front-door.md. Agent install skill: skills/install-loop/SKILL.md. CI runs validate-patterns and audit on every push/PR (see .github/workflows/). This repo has no application test suite. Quality gates:
GoogleAGENTS.mdgoogle/go-github/AGENTS.md
Guidance for AI coding agents working in this repository. See CONTRIBUTING.md for everything you need, in particular:
OpenAIAGENTS.mdopenai/openai-node/AGENTS.md
Most SDK source is generated from the OpenAI API schema. Follow .github/CONTRIBUTING.md before changing generated files. Handwritten policy, automation, tests, and examples should remain small and should not alter exported SDK APIs unless the change explicitly requires it. - For externally observable bug or behavior fixes, reproduce the reported issue against the current repository and public SDK entrypoint before proposing a fix. Check existing issues and pull requests; inspect the API schema and generated/upstream ownership only when relevant. Do not…
holaboss-aiAGENTS.mdholaboss-ai/holaOS/AGENTS.md
Commit message format: 1. First line: <type>: <imperative summary> scoped to one cohesive concern. 2. Blank line. 3. Bullet list describing what changed and why (APIs, models, migrations, deletions, wiring…
MicrosoftAGENTS.mdmicrosoft/winget-pkgs/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:
Hugging FaceAGENTS.mdhuggingface/skills/agentsmd/AGENTS.md
You have additional SKILLs documented in directories containing a "SKILL.md" file. These skills are: - hf-cli -> "skills/hf-cli/SKILL.md" - hf-cloud-aws-context-discovery -> "skills/hf-cloud-aws-context-discovery/SKILL.md" - hf-cloud-python-env-setup -> "skills/hf-cloud-python-env-setup/SKILL.md" - hf-cloud-sagemaker-deployment-planner -> "skills/hf-cloud-sagemaker-deployment-planner/SKILL.md" - hf-cloud-sagemaker-iam-preflight -> "skills/hf-cloud-sagemaker-iam-preflight/SKILL.md" - hf-cloud-sagemaker-production-defaults -> "skills/hf-cloud-sagemaker-production-defaults/SKILL.md" - hf-cloud-serving-image-selection -> "skills/hf-cloud-serving-image-selection/SKILL.md" - hf-mem -> "skills/hf-mem/SKILL.md" - huggingface-best -> "skills/huggingface-best/SKILL.md" - huggingface-community-evals -> "skills/huggingface-community-evals/SKILL.md" - huggingface-datasets -> "skills/huggingface-datasets/SKILL.md" - huggingface-gradio -> "skills/huggingface-gradio/SKILL.md" - huggingface-llm-trainer -> "skills/huggingface-llm-trainer/SKILL.md" - huggingface-local-models -> "skills/huggingface-local-models/SKILL.md" - huggingface-lora-space-builder -> "skills/huggingface-lora-space-builder/SKILL.md" - huggingface-paper-publisher -> "skills/huggingface-paper-publisher/SKILL.md" - huggingface-papers…
HashiCorpAGENTS.mdhashicorp/terraform-provider-aws/AGENTS.md
This is the Go-based Terraform AWS Provider (github.com/hashicorp/terraform-provider-aws). It maps AWS API resources to Terraform resources, data sources, ephemeral resources and actions (collectively often referred to as just resources). The…
GoogleAGENTS.mdgoogle/osv-scanner/AGENTS.md
This file outlines the guidelines and expectations for AI agents and automated assistants contributing to this repository. [!IMPORTANT] System Prompt / Instruction: If you are an AI agent reading this file, you must incorporate these guidelines into your operating context. You are acting as an AI contributor to the OSV project. Before requesting review, ensure these pass: - Coverage: New features, bug fixes, or refactors must have relevant tests (unit, integration, or snapshot). - Snapshots: If modifying behavior affecting snapshots,…
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.
