agentleFS
Sign inSign up

AGENTS.md examples from real projects

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

Best matches · from page 15Worked for most · soon
puppyone-aiAGENTS.md

puppyone-cloud / backend

puppyone-ai/puppyone-cloud/backend/AGENTS.md

export` → `pip install -r requirements.lock.txt` ### Railway 控制台必须设置的项 每个共享本仓库的 service(`api` / `file_worker` / `mcp_server`)都必须把 `Settings -> Service -> Source -> Root Directory` 设成 `backend`(写 `/backend` 也等价)。 否则: - Railway 把整个 monorepo 根当成构建上下文

1.3k13d agoDiscuss
coollabsioAGENTS.md

jean

coollabsio/jean/AGENTS.md

queued prompts (no files/images/skills/text attachments) are steerable. - **Background recovery** mirrors Codex's survivable app-server pattern: host-backed PI runs store the host PID on the run, are treated

1.3k8mo agoReads credentialsDiscuss
sipyourdrink-ltdAGENTS.md

bernstein

sipyourdrink-ltd/bernstein/AGENTS.md

system (pluggy) - `src/bernstein/plugins/` | | `tui/` | Textual TUI - `src/bernstein/tui/` | | `github_app/` | GitHub App integration - `src/bernstein/github_app/` | | `mcp/` | MCP server - `src/bernstein/mcp/` | | `benchmark/` | SWE-bench - `src/bernstein/benchmark/` | ## Directory context files Per-directory context files for agents

1.3k9d agoDiscuss
caliber-ai-orgAGENTS.md

ai-setup

caliber-ai-org/ai-setup/AGENTS.md

Check[]` - No hardcoded mappings — LLM-driven via `src/ai/detect.ts` - `collectFingerprint()` async with LLM enrichment (`src/fingerprint/index.ts`) - MCP server workspace: `packages/mcp-server/` ## Before Committing **IMPORTANT:** Before every git commit, you MUST ensure Caliber syncs

1.3k5mo agoDiscuss
LiteLLM-LabsAGENTS.md

litellm-agent-control-plane

LiteLLM-Labs/litellm-agent-control-plane/AGENTS.md

silently if the network is unavailable — it never blocks a commit. ## MCP integration invariants `mcp_server_ids` (in `AgentDraft`) is the **sole source of truth** for which MCP integrations

1.3k4mo agoDiscuss
MicrosoftAGENTS.md

generative-ai-with-javascript

microsoft/generative-ai-with-javascript/AGENTS.md

install npm start # Interact with characters through the web interface ``` 3. **For MCP lessons, use the inspector tool:** ```bash cd lessons/07-mcp/solution npm run build npm run inspect # Test individual tools

1.3k12mo agoReads credentialsDiscuss
modu-aiAGENTS.md

moai-adk

modu-ai/moai-adk/AGENTS.md

land. After three failures on one operation, report the blocker. **Maintain effectiveness without MCP servers.** Where one is unavailable, fall back to web search and fetch for library documentation

1.2k36d agoDeletes or force-pushesDiscuss
i365devAGENTS.md

free4chat

i365dev/free4chat/AGENTS.md

Agent bootstrap prompt │ │ ├── do/RoomSession.ts # room presence/context/media state │ │ ├── do/meetingNotesAuth.ts # legacy compatibility + media grant decisions │ │ ├── do/realtimeMedia.ts # server-side Cloudflare Realtime track-close │ │ ├── do/ # RoomSession state coordination │ │ ├── hooks/useSfuChatRoom.ts # WebRTC, SFU negotiation, DataChannels │ │ ├── components/RoomContent.tsx

1.2k30d agoReads credentialsDiscuss
Ido-LeviAGENTS.md

Hephaestus

Ido-Levi/Hephaestus/AGENTS.md

Module Organization - `src/` holds the orchestration stack: `agents/` (lifecycle), `memory/` (Qdrant RAG), `mcp/` (FastAPI MCP server), `monitoring/` (Guardian & Conductor loops), and shared utilities in `core/`. - `frontend/` is the Vite + React

1.2k11mo agoReads credentialsDiscuss
matthiasnAGENTS.md

lotti

matthiasn/lotti/AGENTS.md

test file per source file**, mirroring the path. - Run tests via the dart-mcp server, **only for the files you actually touched**. Do not run the whole suite locally

1.2k28d agoReads credentialsDiscuss
xuzhougengAGENTS.md

wisp-science

xuzhougeng/wisp-science/AGENTS.md

computing agent. The long-term product direction is a research workbench: local, WSL, SSH servers, GPU hosts, schedulers, literature tools, runs, data assets, artifacts, papers, and decisions should be represented

1.2k2mo agoDiscuss
DicklesworthstoneAGENTS.md

coding_agent_session_search

Dicklesworthstone/coding_agent_session_search/AGENTS.md

# AGENTS.md — coding_agent_session_search (cass) > Guidelines for AI coding agents working in this

1.1k6d agoReads credentialsDiscuss
agentrqAGENTS.md

agentrq

agentrq/agentrq/AGENTS.md

same goes for code comments. ## Project layout - `backend/` — Go backend (Fiber HTTP, GORM, MCP server) - `frontend/` — Vue3 frontend, and the single source of UI for **both** the web and desktop

1.1k4d agoDiscuss
zhitongblogAGENTS.md

solomd

zhitongblog/solomd/docs/agents.md

workspace root. --- ## Related docs - `docs/roadmap.md` — v4.0 plan + the strategic principles behind the safety model. - `mcp-server/README.md` — the MCP surface for external clients (Claude Desktop, etc.). - `app/src-tauri/src/recipes.rs` — schema definition (Rust

1.1k4mo agoDiscuss
VercelAGENTS.md

eve-software-factory-template

vercel-labs/eve-software-factory-template/AGENTS.md

brain`, gated by `factoryBrainPolicy` so unattended runs can't write shared context). - **Connections** are MCP servers: `linear` (`https://mcp.linear.app/mcp`, app-scoped auth shared through `linearAuth` in `agent/lib/constants.ts`). Its connection

1.1k44d agoReads credentialsDiscuss
matlabAGENTS.md

simulink-agentic-toolkit

matlab/simulink-agentic-toolkit/AGENTS.md

following in MATLAB: ```matlab addpath(' ') setupAgenticToolkit("install") ``` This handles platform detection, MCP server download, toolkit installation, agent configuration, and skill registration. Do not attempt to run setup commands

1.1k5mo agoDiscuss
TencentCloudBaseAGENTS.md

CloudBase-AI-Toolkit

TencentCloudBase/CloudBase-AI-Toolkit/AGENTS.md

PLUGINS` 中解析;旧名称只允许出现在"兼容别名"说明中,不应继续作为主名称书写 - 文档链接必须指向真实存在的仓库文件或站点路由;涉及工具数量时,优先使用不易过期的描述,避免写死数字 # npm 供应链安全(必须遵守) 本项目因 MCP Server + 大规模 AI IDE 技能分发特性,是 npm 供应链攻击的高价值目标。 **强制规则:** - 安全敏感依赖(`@cloudbase/*`、`@modelcontextprotocol/sdk`、express

1.1k45d agoDiscuss
lee-toAGENTS.md

ai-factory

lee-to/ai-factory/AGENTS.md

skill-generator/ # Generate new skills │ └── aif-verify/ # Verify implementation against plan ├── scripts/ # test-skills.sh ├── mcp/ # MCP server templates ├── dist/ # Compiled JS └── bin/ # CLI entry point ``` ## Key Concepts ### Skills Location - **Package skills

1.1k9d agoDiscuss
alibabaAGENTS.md

skill-up

alibaba/skill-up/AGENTS.md

credential values; redact them via the helpers in `internal/credential/`. - External processes (Agent Engines, MCP servers, scripts) run in the selected runtime (`none` or `opensandbox`). When adding new shell execution paths

1.1k5mo agoDiscuss
fastcrwAGENTS.md

crw

fastcrw/crw/AGENTS.md

server"]`). - `crw-mcp-proto` - MCP tool/message definitions, shared by embedded and standalone MCP servers. - `crw-mcp` - standalone MCP server binary. - `crw-browse` - browser-automation MCP server binary

1.1k7mo agoDiscuss
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.