AGENTS.md examples from real projects

fastreplReads credentialsAGENTS.md

anarlog

fastrepl/anarlog/AGENTS.md

api_ci.yaml`: `cargo check -p api`; tests for `api-cloud`, `api-auth`, `mcp`, `supabase-auth --features server`, `api-sync`, `transcribe-proxy --lib`, the API drain test, and the deployment/E2EE Python tests

fastreplAGENTS.md

anarlog

fastrepl/anarlog/docs/AGENTS.md

docs.anarlog.so`. - Write for Anarlog users, developers, and agents using the CLI or MCP server. - Configuration lives in `docs.json`; content pages are MDX. - The public agent skill is served from `skill.md

alibabaReads credentialsAGENTS.md

higress

alibaba/higress/AGENTS.md

repo SDK dir). In-repo, `plugins/wasm-go/pkg/mcp/` provides MCP helpers and `plugins/wasm-go/mcp-servers/` holds MCP server plugins. - `examples/` — reference plugins, including the Go counterparts of C++ plugins. These are excluded from official

usekaneoReads credentialsAGENTS.md

kaneo

usekaneo/kaneo/AGENTS.md

Other entry points: Consider the mobile app, MCP, API keys, webhooks, Docker, Helm, and docs when the behavior reaches them. ## Working safely - Server configuration comes from the root `.env`; Vite

backnotpropReads credentialsAGENTS.md

plannotator

backnotprop/plannotator/AGENTS.md

server implementation │ │ ├── index.ts # startPlannotatorServer(), handleServerReady() │ │ ├── review.ts # startReviewServer(), handleReviewServerReady() │ │ ├── annotate.ts # startAnnotateServer(), handleAnnotateServerReady() │ │ ├── inbox.ts # startInboxServer(), handleInboxServerReady(): the Plannotator Inbox (Bun-only, loopback-only; see "Plannotator Inbox") │ │ ├── inbox-mcp.ts # The Inbox's MCP tools

Model Context ProtocolAGENTS.md

modelcontextprotocol

modelcontextprotocol/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

open-pencilAGENTS.md

open-pencil

open-pencil/open-pencil/AGENTS.md

packages/vue/AGENTS.md` | | `packages/cli` | Headless `.fig` inspection, export, linting, `eval` | `packages/cli/AGENTS.md` | | `packages/mcp` | stdio and Hono HTTP MCP server reusing Core tools | `packages/mcp/AGENTS.md` | | `packages/harness` | Optional Node companion for HarnessAgent sessions | `packages/harness/AGENTS.md` | | `packages/feedback` | Cloudflare

open-pencilAGENTS.md

open-pencil / src

open-pencil/open-pencil/src/AGENTS.md

hold each protocol; a chat's agent reaches OpenPencil's MCP server through `linkChatAgent` in `src/app/integrations/mcp/link.ts`. ACP process changes require checking `desktop/capabilities/**`. - Provider definitions are in `packages/core/src/ai/providers.ts`, exported from `@open

open-pencilAGENTS.md

open-pencil / tests

open-pencil/open-pencil/tests/AGENTS.md

stay local; only genuinely shared support goes under central `tests/helpers/ /` and `tests/fixtures/`. MCP transport tests: `tests/engine/mcp/{server,stdio,transport}` with `tests/helpers/mcp`. - Never commit temporary, diagnostic, or profile specs; keep them

pocoprojectAGENTS.md

poco

pocoproject/poco/AGENTS.md

agents/local/`, which git ignores (see [local notes](ai-agents/README.md#local-notes)). MCP server registrations that carry credentials (`.mcp.json`) are never committed. ## Project POCO (Portable Components

LearningCircuitAGENTS.md

local-deep-research

LearningCircuit/local-deep-research/AGENTS.md

thread lifecycle, QueuePool/FD budget, and cleanup model. ## Where to look | Task | Paths | | --- | --- | | Backend and server lifecycle | `src/local_deep_research/web/app.py`, `src/local_deep_research/web/fastapi_app.py`, `src/local_deep_research/web/routers/`, `src/local_deep_research/web/services/` | | Auth and sessions | `src/local_deep_research/web/auth/`, `src/local_deep_research/database/encrypted_db.py` | | Settings | `src/local_deep_research/settings/`, `src/local_deep_research/settings/env_definitions/`, `src/local_deep_research/web/routers/settings.py`, `src/local_deep_research/defaults

MervinPraisonAGENTS.md

PraisonAI

MervinPraison/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

No other project uses it yet

rehan-remadeReads credentialsAGENTS.md

universal-modder

rehan-remade/universal-modder/AGENTS.md

rawfiles out of your own `.ff` zones, PNG ↔ IWI textures, weapon-file edits - **fal MCP server:** `https://mcp.fal.ai/mcp` with header `Authorization: Bearer $FAL_KEY`. - It's pre-configured

CloudflareReads credentialsAGENTS.md

vinext

cloudflare/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

maximhqReads credentialsAGENTS.md

bifrost

maximhq/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

miurlaReads credentialsAGENTS.md

morphic

miurla/morphic/AGENTS.md

project supports MCP for enhanced AI assistant integration with Next.js 16. ### Built-in Next.js MCP Server Next.js 16 provides a built-in MCP server at `http://localhost:3000/_next/mcp` when

openstatusHQAGENTS.md

openstatus

openstatusHQ/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

kunchenguidAGENTS.md

no-mistakes

kunchenguid/no-mistakes/AGENTS.md

parser; the reviewer writes with its own file tools, so there is deliberately no MCP server. That package therefore owns `AppendAnswer` (the daemon's answer handler) and NO question writer

tsparticlesAGENTS.md

tsparticles

tsparticles/tsparticles/AGENTS.md

exec nx test`) - avoids using globally installed CLI - You have access to the Nx MCP server and its tools, use them to help the user - For Nx plugin best practices

No other project uses it yet

strands-agentsAGENTS.md

sdk-python

strands-agents/sdk-python/AGENTS.md

/AGENTS.md ├── strands-ts/ # TypeScript SDK (npm workspace) — see strands-ts/AGENTS.md ├── strands-mcp/ # MCP server with Strands docs for coding agents (hatch) ├── site/ # Documentation site (Astro) — see site/AGENTS.md ├── team/ # Governance

No other project uses it yet