How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
BeehiveInnovationsAGENTS.mdBeehiveInnovations/pal-mcp-server/AGENTS.md
requirements-dev.txt` Also read CLAUDE.md and CLAUDE.local.md if available. ## Project Structure & Module Organization PAL MCP Server centers on `server.py`, which exposes MCP entrypoints and coordinates multi-model workflows. Feature-specific tools
MemTensorAGENTS.mdMemTensor/MemOS/AGENTS.md
parsers/` `reranker/` | Provider implementations (`base.py` + `factory.py` + each backend) | | `src/memos/api/` | FastAPI service (routers / handlers / middleware / MCP server) | | `src/memos/configs/` | All pydantic configuration classes (one-to-one with the modules above) | | `src/memos/context/` | Cross
cocoindex-ioAGENTS.mdcocoindex-io/cocoindex/AGENTS.md
status` to confirm the root is this repo. We register no MCP server on purpose — an `ccc mcp` mode exists, but the CLI costs no context until invoked and behaves
Model Context ProtocolAGENTS.mdmodelcontextprotocol/inspector/AGENTS.md
Inspector V2 This is an application for inspecting MCP servers. It has three incarnations — Web, TUI, and CLI — over a shared `core/`. **This file holds the _rules_: the conventions
MicrosoftAGENTS.mdmicrosoft/fluentui-system-icons/AGENTS.md
affected`) instead of using the underlying tooling directly - You have access to the Nx MCP server and its tools, use them to help the user - When answering questions about
GoogleAGENTS.mdgoogle/adk-recipes/core/python/genmedia-for-commerce/AGENTS.md
Gemini, pushed to GCS, inline bytes replaced with [user_upload | filename | description] -> McpToolset -> GenMedia MCP server (mcp_server/server.py, 7 tools) - before_tool_callback resolves filenames -> base64 from GCS -> media workflow
GoogleAGENTS.mdgoogle/adk-recipes/core/python/long-horizon-harness/AGENTS.md
gateways (Telegram/Discord/Slack/WhatsApp/Signal), sandbox backends other than the managed Sandboxes backend + local fallback, browser/computer-use/image-gen/video-gen/TTS/voice tools, MCP server, TUI, ACP. ## Project Layout ``` lha/ ├── horizon/ # importable Python package (`import horizon`); outer repo
CloudflareAGENTS.mdcloudflare/cloudflare-os/AGENTS.md
code under `files/`, which may be TypeScript. * packages/workshop-shared: Shared API definitions between client and server. * This defines the application's RPC interface. * The RPC protocol is Cap'n Web, which
open-gsdAGENTS.mdopen-gsd/gsd-core/docs/AGENTS.md
chrome-devtools-mcp` package), driven from `Bash` against a throwaway `--isolated` profile: no MCP server, no `tools:` change. It needs an installed Chrome (`CHROME_BIN` overrides discovery). With
AWSAGENTS.mdawslabs/mcp/src/dynamodb-mcp-server/AGENTS.md
AGENTS.md ## Project Overview This is the **AWS DynamoDB MCP Server** - an official AWS Labs Model Context Protocol (MCP) server that provides DynamoDB expert design guidance and data modeling assistance
Model Context ProtocolAGENTS.mdmodelcontextprotocol/modelcontextprotocol/AGENTS.md
symlink at `docs/.mintlify/skills/ ` pointing to `../../../plugins/ /skills/ ` so Mintlify's `.well-known/agent-skills/` and MCP server auto-scan exposes it. ## Useful Commands ```bash # Dev servers npm run serve:docs # Local
openstatusHQAGENTS.mdopenstatusHQ/openstatus/AGENTS.md
connected to this repository and available to coding agents through the [Polylane MCP server](https://mcp.polylane.com/mcp). - When a question involves production behaviour (an error, a spike, a deploy
MervinPraisonAGENTS.mdMervinPraison/PraisonAI/AGENTS.md
fine-tuning + agent training in `praisonai-train/`, browser automation in `praisonai-browser/`, MCP server host in `praisonai-mcp/`, sandbox backends in `praisonai-sandbox/`, deployment in `praisonai-deploy/`, integrations/serve/dashboard
backnotpropAGENTS.mdbacknotprop/plannotator/AGENTS.md
# Plannotator A plan review UI for Claude Code that intercepts `ExitPlanMode` via hooks, letting
CloudflareAGENTS.mdcloudflare/vinext/AGENTS.md
leave known bugs as "follow-ups" — fix them in the same PR. ### Debugging - **Dev server logs**: Run `npx vite dev` in a fixture directory - **RSC streaming issues**: Context is often
GoogleAGENTS.mdgoogle/adk-go/AGENTS.md
auth providers for outbound requests - `agentregistry/` Client for Google Cloud Agent Registry (A2A agents, MCP servers, models) - `plugin/` Cross-cutting lifecycle hooks; `plugin/agentanalytics` is a separate module - `server/` HTTP servers
apifyAGENTS.mdapify/apify-mcp-server/AGENTS.md
Apify MCP server TypeScript, ES modules. Runs in two modes: **stdio** (local CLI clients, `stdio.ts`) and **HTTP Streamable** (`dev_server.ts`). **Before implementing**: work from an issue that is assigned or explicitly
apifyAGENTS.mdapify/apify-mcp-server/src/AGENTS.md
index_internals_test_kit.ts` — the separate `./internals/test-kit.js` surface for `tests/test_kit/**`'s own self-reference imports only; apify-mcp-server-internal doesn't consume it, don't add anything here it does. - `stdio.ts
strands-agentsAGENTS.mdstrands-agents/harness-sdk/strands-py/AGENTS.md
while the SDK was *running* that an operator would want in their logs (an MCP server failed to start, a tool failed to load, a store write failed). These
maximhqAGENTS.mdmaximhq/bifrost/AGENTS.md
configuration │ │ ├── plugins.go # Plugin CRUD │ │ ├── cache.go # Cache management │ │ ├── session.go # Auth/session management │ │ ├── health.go # Health checks │ │ ├── mcpserver.go # MCP server (SSE/streamable HTTP) │ │ ├── websocket.go # WebSocket handler │ │ ├── devpprof.go # Pool debug profiler endpoint (~23KB) │ │ └── middlewares.go # Middleware definitions
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.
