AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Worked for most · soon

vllm-project 10k+ stars

vllm-projectPipes a download into a shellAGENTS.md

vllm

vllm-project/vllm/AGENTS.md

These instructions apply to all AI-assisted contributions to vllm-project/vllm. Breaching these guidelines can result in automatic banning. Before proposing a PR, run these checks: Do not open one-off PRs for tiny edits (single typo, isolated style change, one mutable default, etc.). Mechanical cleanups are acceptable only when bundled with substantive work. - Pure code-agent PRs are not allowed. A human submitter must understand and defend the change end-to-end. - The submitting human must review every changed line and run relevant…

2 projects use a version of this

97k12d agoReviewMount

vllm-projectAGENTS.md

vllm / rust

vllm-project/vllm/rust/AGENTS.md

This project implements an alternative, Rust-native frontend to the vLLM Engine. It is still experimental and actively evolving. The Python frontend is the behavioral reference for the OpenAI-compatible API; see Python frontend parity. Requests flow HTTP/gRPC DTO → chat or text request → engine request. Dependencies point downward: lower crates know nothing about the crates above them. Put a rule in the crate that owns its semantics, even if only one protocol triggers it today. The remaining crates are tooling…

2 projects use a version of this

97k12d agoReviewMount

vllm-projectAGENTS.md

vllm / tests

vllm-project/vllm/tests/AGENTS.md

- Test real objects on the lightest real path. Construct vLLM objects with their real constructors; do not stand them in with SimpleNamespace or MagicMock, set private attributes, or patch methods to reach a state. Mock only external services. Pick the cheapest setup that exercises the change: a layer or kernel test does not need vllm_runner, and single-rank parallel state is enough when parallelism is irrelevant. A fix to user-visible behavior needs at least one regression test through LLM (vllm_runner)…

Surging2 mentions in 2 weeks

1 project uses a version of this

97k12d agoReviewMount

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.