AGENTS.md examples from real projects

DeepSeekAGENTS.md

deepseek-harness / experimental

deepseek-ai/deepseek-harness/packages/experimental/AGENTS.md

through `devDependencies`; examples may load them explicitly. - Experimental status does not relax engineering, security, documentation, lifecycle, testing, or snapshot requirements. - Publishing an experimental package does not promote

No other project uses it yet

DeepSeekAGENTS.md

deepseek-harness / website

deepseek-ai/deepseek-harness/website/AGENTS.md

AGENTS.md — Documentation website adapter Follow the [root instructions](../AGENTS.md), the [documentation standard](../docs/AGENTS.md), and the [documentation workflow](../.agents/skills/dsh-doc-writing/SKILL.md). ## Keep documentation content out of this tree `website/` owns only VitePress configuration

NousResearchAGENTS.md

hermes-agent / plugins

NousResearch/hermes-agent/plugins/AGENTS.md

VERSION`, a manifest-wide native `api:` match, or version literals on unrelated payloads. Documented surfaces stay additive: - Hook payload data is added as **keyword fields**; callbacks are signature-inspected

affaan-mAGENTS.md

ECC

affaan-m/ECC/AGENTS.md

Playwright testing | Critical user flows | | refactor-cleaner | Dead code cleanup | Code maintenance | | doc-updater | Documentation and codemaps | Updating docs | | cpp-reviewer | C/C++ code review | C and C++ projects | | cpp-build

No other project uses it yet

n8n-ioReads credentialsAGENTS.md

n8n

n8n-io/n8n/AGENTS.md

voice, and one instruction for each sentence - **JSDoc on `@Env(...)` config properties is public documentation.** The docs team exports these comments into the environment variable reference on docs.n8n.io. Write them

MicrosoftAGENTS.md

vscode / agentHost

microsoft/vscode/src/vs/platform/agentHost/AGENTS.md

upstream, and preserve compatibility with alternate hosts and UIs. > Node runtime service construction is documented separately in [`node/serviceBootstrapping.md`](node/serviceBootstrapping.md). Host startup timings, process-lifetime correlation, and session workload counts

MicrosoftAGENTS.md

vscode / prompts

microsoft/vscode/src/vs/platform/agentHost/node/copilot/prompts/AGENTS.md

tools registered by Agent Host. This internal debugging setting assumes those values use the documented string shape. > **Launch-time freeze.** The SDK accepts a system message only at session create/resume

No other project uses it yet

instructkrReads credentialsAGENTS.md

claude-code

instructkr/claude-code/AGENTS.md

file changes (path filters) - CI clippy job runs without `-D warnings` — weaker than the documented gate; known pre-existing failures recorded in docs/g002/g003 maps - `claw acp` is a status stub

avelinoAGENTS.md

awesome-go

avelino/awesome-go/AGENTS.md

awesome-go · LLM Contribution Guide This document summarizes the project context and the conventions that language models must follow when helping on this repository. ## Project Snapshot - Purpose: maintain the curated

No other project uses it yet

Significant-GravitasAGENTS.md

AutoGPT

Significant-Gravitas/AutoGPT/AGENTS.md

autogpt_platform/frontend` – Next.js + Typescript frontend. - `autogpt_platform/docker-compose.yml` – development stack. See `docs/platform/getting-started.md` for setup instructions. ## Documentation - `docs/home/`, `docs/platform/` and `docs/integrations/` are the public docs site (agpt.co/docs). Only pages written

Significant-GravitasReads credentialsAGENTS.md

AutoGPT / autogpt_platform

Significant-Gravitas/AutoGPT/autogpt_platform/AGENTS.md

support - **Frontend** (`frontend`): Next.js React application - **Shared Libraries** (`autogpt_libs`): Common Python utilities ## Component Documentation - **Backend**: See @backend/AGENTS.md for backend-specific commands, architecture, and development tasks - **Frontend**: See @frontend/AGENTS.md

No other project uses it yet

Significant-GravitasAGENTS.md

AutoGPT / vercel-react-best-practices

Significant-Gravitas/AutoGPT/.claude/skills/vercel-react-best-practices/AGENTS.md

React Best Practices **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

Significant-GravitasAGENTS.md

AutoGPT

Significant-Gravitas/AutoGPT/docs/AGENTS.md

Documentation Guidelines ## Where a Document Goes - **Published pages** live in `docs/home/`, `docs/platform/` and `docs/integrations/`. GitBook publishes them at agpt.co/docs, and a page appears on the site once that folder

No other project uses it yet

Hugging FaceAGENTS.md

transformers

huggingface/transformers/.ai/AGENTS.md

only if it affects real use: a published checkpoint, a default config, or a documented workflow. For example, an exception when `n_groups > 1` in a model whose published checkpoints

langgeniusAGENTS.md

dify / api

langgenius/dify/api/AGENTS.md

testing) when adding or moving unit tests. ## Architecture And Boundaries Read all backend architecture documentation before modifying backend code: - [Backend architecture][architecture] - [Repositories][repositories] - [SQLAlchemy][sqlalchemy] - [Database schema][db-schema

No other project uses it yet

langgeniusAGENTS.md

dify / cli

langgenius/dify/cli/AGENTS.md

commands`) own state. A plugin's `build()` closes over its own cache or loaded document; nothing outside a plugin reaches into another plugin's internals. Outside a plugin folder, import

No other project uses it yet

langgeniusAGENTS.md

dify / dify-agent

langgenius/dify/dify-agent/AGENTS.md

package's `uv` environment and Pydantic v2 APIs. Inspect current dependency source or official documentation before integrating, implementing, or mocking an API whose runtime contract is not established locally. ## Tests

langflow-aiAGENTS.md

langflow

langflow-ai/langflow/AGENTS.md

Reference any issues fixed (e.g., `Fixes #1234`) - Ensure all tests pass before submitting ## Documentation Documentation uses Docusaurus and lives in `docs/`: ```bash cd docs yarn install yarn start # Dev server

LangChainReads credentialsAGENTS.md

langchain

langchain-ai/langchain/AGENTS.md

Global development guidelines for the LangChain monorepo This document provides context to understand the LangChain Python project and assist with development. ## Corridor security analysis When Corridor's `analyzePlan` tool

No other project uses it yet

comfyanonymousAGENTS.md

ComfyUI

comfyanonymous/ComfyUI/AGENTS.md

Avoid caller-side unwrapping such as `out = out[0]` unless the called interface is documented to return that structure. ## Autograd and Model Freezing - Do not add `torch.no_grad`, `torch.inference_mode