AGENTS.md examples from real projects

TencentAGENTS.md

WeKnora / cli

Tencent/WeKnora/cli/AGENTS.md

sentinel) - `internal/sse/` — `Accumulator` for chat / session ask SSE streams - `internal/mcp/` — curated 10-tool stdio MCP server (wired by `cmd/mcp/serve.go`); see [MCP tool surface](#mcp-tool-surface) for the curation rationale

AnthropicAGENTS.md

knowledge-work-plugins / zoom-plugin

anthropics/knowledge-work-plugins/partner-built/zoom-plugin/AGENTS.md

workflow for Claude ## Repo Shape - `.claude-plugin/plugin.json` — Claude plugin manifest - `.mcp.json` — bundled Zoom MCP server definition - `skills/` — all plugin skills and supporting references - `README.md` — user-facing overview - `CONNECTORS.md` — bundled

No other project uses it yet

jdxReads credentialsAGENTS.md

mise

jdx/mise/AGENTS.md

other hk steps do not run there. ### hk Agent Workflow - Prefer the hk MCP server for effect-aware plans, checks, fixes, logs, and captured diffs. - When invoking hk directly

alibabaAGENTS.md

nacos

alibaba/nacos/AGENTS.md

Remote Agent Discovery Protocol Spec](./specs/en/ai/rad-protocol-spec.md), [Agent API Spec](./specs/en/ai/agent-api-spec.md), [Agent Storage Spec](./specs/en/ai/agent-storage-spec.md), [MCP Server Spec](./specs/en/ai/mcp-server-spec.md), [A2A Agent Spec](./specs/en/ai/a2a-agent-spec.md), [Prompt Spec](./specs/en/ai/prompt-spec.md), [Skill Spec](./specs/en/ai/skill-spec.md), [AgentSpec Spec

No other project uses it yet

storytoldReads credentialsAGENTS.md

craft-anything

storytold/craft-anything/AGENTS.md

helps them rebuild it. It ships a desktop app (egui), a CLI and an MCP server, all driven by one engine. Display name **Craft Anything**; machine names `craft-anything-*`; bundle

topoteretesReads credentialsAGENTS.md

cognee

topoteretes/cognee/AGENTS.md

search "..." # low level uv run cognee-cli -ui # Launches UI, backend API, and MCP server together ``` - Start the FastAPI server directly: ```bash uv run python -m cognee.api.client ``` - Run tests

No other project uses it yet

onyx-dot-appAGENTS.md

onyx / web

onyx-dot-app/onyx/web/AGENTS.md

react-icons`. If an icon is missing, import it from Figma with the Figma MCP tool and add it to `lib/opal/src/icons/`. - Hover-reveal: `Hoverable` from `@opal/core`. If you must hand

getzepReads credentialsAGENTS.md

graphiti

getzep/graphiti/AGENTS.md

Service adapters and API glue reside in `server/graph_service/`, while the MCP integration lives in `mcp_server/` (with its own `src/`, `tests/`, `config/`, and `docker/` subdirectories). Shared assets sit in `images

garrytanPipes a download into a shellAGENTS.md

gbrain

garrytan/gbrain/AGENTS.md

turn brain-first rule and leaves the MCP entry alone; agents seldom call an MCP server nobody told them about. The installer is a shell script for macOS and Linux

No other project uses it yet

supermemoryaiReads credentialsAGENTS.md

supermemory

supermemoryai/supermemory/AGENTS.md

Path | What it is | | --- | --- | | `apps/web/` | Redirects to the console (needs no env) | | `apps/mcp/` | The MCP server (workspace `supermemory-mcp`; not the npm package of that name). Hosted at `https://mcp.supermemory.ai

VercelAGENTS.md

turborepo / apps

vercel/turborepo/apps/docs/AGENTS.md

behavior, analytics, and the Remote Cache page action app-owned. - Do not advertise an MCP server unless Turborepo provides one. # This is NOT the Next.js you know This version

LangChainAGENTS.md

deepagents

langchain-ai/deepagents/AGENTS.md

langchain-ai/docs` repo; a local checkout supports file search, and the docs MCP server is configured in `.mcp.json` ## OpenWiki This repository has a generated `openwiki/` evidence index

No other project uses it yet

LangChainReads credentialsAGENTS.md

deepagents / code

langchain-ai/deepagents/libs/code/AGENTS.md

picker — the *model-selector filter* (`model_selector.py`), *thread-selector filter* (`thread_selector.py`), and *MCP viewer filter* (`#mcp-filter`, `mcp_viewer.py`). A specialized modal field; call it a "filter input" when the point

heroui-incAGENTS.md

heroui

heroui-inc/heroui/AGENTS.md

skip it deliberately otherwise. Add a `*.ssr.test.tsx` when the component renders on the server path: it is exported for use outside `"use client"` boundaries, reads `document`/`window` during render, generates

No other project uses it yet

OpenAIAGENTS.md

openai-agents-python

openai/openai-agents-python/AGENTS.md

then the affected references. That map owns routing for agents/context, runner/items, schemas, tools, MCP, providers, conversation/session/RunState persistence, tracing, Realtime, voice, and sandbox lifecycle. - Keep `src/agents/run.py` focused on orchestration/public flow

OpenAIAGENTS.md

openai-agents-python

openai/openai-agents-python/docs/agents.md

tool_choice`. | | `tools` | no | Tools the agent can call. See [Tools](tools.md). | | `mcp_servers` | no | MCP servers that provide MCP-backed tools to the agent. See the [MCP guide](mcp.md

OpenAIAGENTS.md

openai-agents-python / ja

openai/openai-agents-python/docs/ja/agents.md

settings` | いいえ | `temperature`、`top_p`、`tool_choice` などのモデル調整パラメーターです。 | | `tools` | いいえ | エージェントが呼び出せるツールです。[ツール](tools.md)を参照してください。 | | `mcp_servers` | いいえ | MCPを基盤とするツールをエージェントに提供する MCPサーバーです。[MCPガイド](mcp.md)を参照してください。 | | `mcp_config` | いいえ | スキーマの strict モードへの変換や MCPの失敗の書式設定など、MCPツールの準備方法を細かく調整します

OpenAIAGENTS.md

openai-agents-python / ko

openai/openai-agents-python/docs/ko/agents.md

모델 조정 매개변수 | | `tools` | 아니요 | 에이전트가 호출할 수 있는 도구입니다. [도구](tools.md)를 참조하세요. | | `mcp_servers` | 아니요 | 에이전트에 MCP 기반 도구를 제공하는 MCP 서버입니다. [MCP 가이드](mcp.md)를 참조하세요. | | `mcp

OpenAIAGENTS.md

openai-agents-python / zh

openai/openai-agents-python/docs/zh/agents.md

模型调优参数，例如 `temperature`、`top_p` 和 `tool_choice`。 | | `tools` | 否 | 智能体可以调用的工具。请参阅[工具](tools.md)。 | | `mcp_servers` | 否 | 为智能体提供 MCP 支持工具的 MCP 服务器。请参阅 [MCP 指南](mcp.md)。 | | `mcp_config` | 否 | 微调

h4ckf0r0dayAGENTS.md

obscura

h4ckf0r0day/obscura/AGENTS.md

fetch` (`--dump assets|html|text|links|markdown|original|cookies`, `--eval `, `--screenshot `), `serve` (CDP server), `scrape`, `mcp`. `--proxy`, `--stealth`, and `--allow-private-network` are global flags: valid before or after

No other project uses it yet