agentleFS
Sign inSign up

AGENTS.md examples from real projects

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

Most stars first · from page 18Worked for most · soon
MicrosoftAGENTS.md

ai-agents-for-beginners / zh-CN

microsoft/ai-agents-for-beginners/translations/zh-CN/AGENTS.md

本仓库包含“初学者的AI代理”——一个全面的教育课程,教授构建AI代理所需的全部知识。课程包含18节课(编号00-18),涵盖基础知识、设计模式、框架、生产部署、本地/设备端代理以及AI代理的安全性。 关键技术: - Python 3.12+ - 用于交互式学习的Jupyter笔记本 - AI框架:微软代理框架(Microsoft Agent Framework,MAF) - Azure AI服务:Microsoft Foundry,Microsoft Foundry Agent Service V2 架构: - 基于课程的结构(00-15+ 目录) - 每节课包含:README文档、代码示例(Jupyter笔记本)和图片 - 通过自动翻译系统支持多语言 - 每节课一个使用微软代理框架的Python笔记本 对于 Microsoft Foundry(必填): - AZUREAIPROJECTENDPOINT - Microsoft Foundry项目端点 - AZUREAIMODELDEPLOYMENT_NAME - 模型部署名称(例如 gpt-5-mini) 对于 Azure AI Search(第五课 - RAG): - AZURESEARCHSERVICEENDPOINT - Azure AI Search端点 - AZURESEARCHAPIKEY - Azure AI Search API密钥 认证:运行 az login 后再运行笔记本(使用 AzureCliCredential)。 每节课程包含多个适用于不同框架的Jupyter笔记本: 微软代理框架 + Microsoft Foundry: - 需要Azure订阅 - 使用 FoundryChatClient 访问Agent Service V2(代理可见于Foundry门户) -…

75k3mo agoReads credentialsDiscuss
MicrosoftAGENTS.md

ai-agents-for-beginners / zh-HK

microsoft/ai-agents-for-beginners/translations/zh-HK/AGENTS.md

本存儲庫包含「AI 初學者代理人」——一個全面的教育課程,教授建立 AI 代理人所需的一切。課程包含 18 課題(編號 00-18),涵蓋基礎知識、設計模式、框架、生產部署、本地/裝置代理人,以及 AI 代理人的安全性。 關鍵技術: - Python 3.12+ - 使用 Jupyter 筆記本進行互動學習 - AI 框架:Microsoft Agent Framework (MAF) - Azure AI 服務:Microsoft Foundry、Microsoft Foundry Agent Service V2 架構: - 基於課程的結構(00-15+ 目錄) - 每課包含:README 文件、代碼範例(Jupyter 筆記本)和圖片 - 通過自動翻譯系統支持多語言 - 每課有一個使用 Microsoft Agent Framework 的 Python 筆記本 用於 Microsoft Foundry(必填): - AZUREAIPROJECTENDPOINT - Microsoft Foundry 專案端點 - AZUREAIMODELDEPLOYMENT_NAME - 模型部署名稱(如 gpt-5-mini) 用於 Azure AI Search(第 05 課 - RAG): - AZURESEARCHSERVICEENDPOINT - Azure AI Search 端點 -…

75k3mo agoReads credentialsDiscuss
MicrosoftAGENTS.md

ai-agents-for-beginners / zh-MO

microsoft/ai-agents-for-beginners/translations/zh-MO/AGENTS.md

本儲存庫包含「初學者 AI 代理人」— 一個全面的教育課程,教授建構 AI 代理人所需的一切。課程由 18 課(編號 00-18)組成,涵蓋基礎、設計模式、框架、產品部署、本地/裝置代理人與 AI 代理人安全性。 關鍵技術: - Python 3.12 以上 - 用於互動學習的 Jupyter 筆記本 - AI 框架:Microsoft 代理框架(MAF) - Azure AI 服務:Microsoft Foundry、Microsoft Foundry 代理服務 V2 架構: - 以課程為基礎的結構(00-15+ 資料夾) - 每課包含:README 文件、程式碼範例(Jupyter 筆記本)與圖片 - 透過自動翻譯系統支援多語言 - 每課一個使用 Microsoft 代理框架的 Python 筆記本 對於 Microsoft Foundry(必需): - AZUREAIPROJECTENDPOINT - Microsoft Foundry 專案端點 - AZUREAIMODELDEPLOYMENT_NAME - 模型部署名稱(例如:gpt-5-mini) 對於 Azure AI Search(第五課 - RAG): - AZURESEARCHSERVICEENDPOINT - Azure AI Search 端點 - AZURESEARCHAPIKEY - Azure AI Search…

75k3mo agoReads credentialsDiscuss
MicrosoftAGENTS.md

ai-agents-for-beginners / zh-TW

microsoft/ai-agents-for-beginners/translations/zh-TW/AGENTS.md

此儲存庫包含「初學者的 AI 代理人」— 一門全面的教育課程,教授構建 AI 代理人所需的一切。該課程包含18個課程(編號00-18),涵蓋基礎知識、設計模式、框架、正式部署、本地/裝置代理人以及 AI 代理人的安全性。 主要技術: - Python 3.12+ - 用於互動學習的 Jupyter 筆記本 - AI 框架:Microsoft Agent Framework (MAF) - Azure AI 服務:Microsoft Foundry、Microsoft Foundry Agent Service V2 架構: - 以課程為基礎的結構(00-15+ 資料夾) - 每個課程包含:README 文件、程式碼範例(Jupyter 筆記本)和圖片 - 透過自動翻譯系統支援多語言 - 每課一個使用 Microsoft Agent Framework 的 Python 筆記本 對於 Microsoft Foundry(必填): - AZUREAIPROJECTENDPOINT - Microsoft Foundry 專案端點 - AZUREAIMODELDEPLOYMENT_NAME - 模型部署名稱(例如 gpt-5-mini) 對於 Azure AI Search(第05課 - RAG): - AZURESEARCHSERVICEENDPOINT - Azure AI Search 端點 - AZURESEARCHAPIKEY - Azure…

75k3mo agoReads credentialsDiscuss
ruvnetAGENTS.md

ruflo

ruvnet/ruflo/AGENTS.md

For OpenAI Codex CLI - Agentic AI Foundation standard Skills: $skill-name | Config: .agents/config.toml Workflow (Use MCP Tools): 1. memorysearch(query="task keywords") → LEARN from past patterns (score > 0.7 = use it) 2. swarminit(topology="hierarchical") → coordination record (instant) 3. YOU write the code / run the commands ← THIS IS WHERE WORK HAPPENS 4. memory_store(key="pattern-x", value="what worked", namespace="patterns") → REMEMBER for next time Ruflo is the coordination ledger and policy decision point. Codex agents are the executors. Coordination records do…

73k21d agoReads credentialsDiscuss
career-ops-hqAGENTS.md

career-ops

career-ops-hq/career-ops/AGENTS.md

Built and used by santifer to evaluate 740+ offers, generate 100+ tailored CVs, and land a Head of Applied AI role. The archetypes, scoring, and negotiation scripts reflect that search; his portfolio is also open source: cv-santiago. It works out of the box, but it's designed to be made yours. You (AI Agent) can edit the user's files: they say "change the archetypes to data engineering roles" and you do it. That's the whole point. Two layers — full list…

73k35d agoDiscuss
career-ops-hqAGENTS.md

career-ops / web

career-ops-hq/career-ops/web/AGENTS.md

The web app is a view over the user's own files, not a second engine. Read this before changing anything under web/. 1. Orchestrate the core; never reimplement it. The CLI already resolves tracker paths, matches tailored CVs and canonicalises statuses: call it, or mirror it behind a parity test. A second implementation of the same rule is how the two halves start disagreeing, and the disagreement is always silent. web/src/lib/core/ holds the access layer for exactly this. 2. Markdown…

73k35d agoDiscuss
colbymchenryAGENTS.md

codegraph

colbymchenry/codegraph/AGENTS.md

Canonical project guidance for coding agents working in this repository (Codex/Astra, Claude Code via @AGENTS.md, Cursor, etc.). Codex size note: root AGENTS.md is intentionally kept near ~35 KiB (critical build/test/arch/retrieval rules retained). Longer validation methodology + the Excalidraw worked example live in docs/AGENTS.md. This environment sets projectdocmax_bytes = 49152 so root (and root+docs/ when cwd is under docs/) are not silently truncated at the 32 KiB default. CodeGraph is a local-first code intelligence library + CLI + MCP server. It…

72k57d agoDeletes or force-pushesDiscuss
colbymchenryAGENTS.md

codegraph

colbymchenry/codegraph/docs/AGENTS.md

Nested Codex guidance under docs/. Loaded with the repo-root AGENTS.md when cwd is under docs/ (Codex walks root to cwd; shared projectdocmax_bytes budget). Root AGENTS.md already carries the non-negotiable retrieval principles (adapt-the-tool, explore budgets, end-to-end synthesis). This file holds the longer validation methodology and Excalidraw worked example that were moved out of root to fit the budget. For each language × framework, validate on small, medium, and large real repos with ≥3 different flow prompts each:

72k57d agoDiscuss
diegosouzapwAGENTS.md

OmniRoute

diegosouzapw/OmniRoute/AGENTS.md

Single source of truth. This file holds ALL project rules, conventions, architecture notes and Hard Rules for every AI assistant working this repository (Claude Code, Gemini, Codex, Copilot, and any other agent). CLAUDE.md and GEMINI.md only add assistant-specific deltas and point back here. When a rule needs to change, change it HERE — never re-fork it into an assistant-specific file. Run the most focused test for changed code first: Other suites: npm run test:e2e, npm run test:protocols:e2e, npm run test:ecosystem.

71k13d agoReads credentialsDiscuss
code-yeongyuAGENTS.md

oh-my-openagent

code-yeongyu/oh-my-openagent/.agents/AGENTS.md

Generated: 2026-08-24 / f3642fcda Project-scope skills + slash commands under the new .agents/ directory name. During the oh-my-opencode → oh-my-openagent rename transition, this directory is the target of the migration…

70k11d agoDiscuss
code-yeongyuAGENTS.md

oh-my-openagent

code-yeongyu/oh-my-openagent/AGENTS.md

HOLD THE FUCK UP. THIS ENTIRE GODDAMN CODEBASE IS BEING RIPPED APART AND REBUILT RIGHT NOW. A MASSIVE MULTI-HARNESS AGENT OS REFACTOR IS IN PROGRESS — WE ARE RESTRUCTURING EVERYTHING…

70k11d agoReads credentialsDiscuss
code-yeongyuAGENTS.md

oh-my-openagent / assets

code-yeongyu/oh-my-openagent/assets/AGENTS.md

Checked-in JSON artifacts consumed by editors, CLIs, installers, and published packages. This directory is output, not the source of configuration or help contracts.

70k11d agoDiscuss
code-yeongyuAGENTS.md

oh-my-openagent / bin

code-yeongyu/oh-my-openagent/bin/AGENTS.md

Node-side launch surface for every public CLI alias. The root shim resolves a platform package and spawns its generated bin/oh-my-opencode.js launcher payload; it is not the TypeScript CLI implementation. oh-my-opencode.js…

70k11d agoDiscuss
code-yeongyuAGENTS.md

oh-my-openagent

code-yeongyu/oh-my-openagent/docs/AGENTS.md

Generated: 2026-08-24 / f3642fcda 30 tracked Markdown files across 6 subdirectories (guide 7, reference 18, examples 3 JSONC, legal 2, templates 1, troubleshooting 1) + root files. Categorized by audience:…

70k11d agoDiscuss
code-yeongyuAGENTS.md

oh-my-openagent

code-yeongyu/oh-my-openagent/.opencode/AGENTS.md

Generated: 2026-08-24 Project-scope OpenCode configuration: 4 skills and 5 slash commands committed alongside the source. Picked up by packages/omo-opencode/src/features/opencode-skill-loader/ and the slash-command discovery pipeline. Relationship to .agents/: .agents/ is the…

70k11d agoDiscuss
code-yeongyuAGENTS.md

oh-my-openagent / packages

code-yeongyu/oh-my-openagent/packages/AGENTS.md

Generated: 2026-08-24 / f3642fcda 45 sibling packages across 6 roles. omo-opencode is the build entry for the main npm dist (packages/omo-opencode/src/index.ts → bundled into root dist/). The root package.json files…

70k11d agoDiscuss
code-yeongyuAGENTS.md

oh-my-openagent / script

code-yeongyu/oh-my-openagent/script/AGENTS.md

Generated: 2026-08-24 Build, publish, QA, and repo-invariant automation. Run via bun run <script> from root package.json. Singular directory name (not "scripts/" -- the root scripts/ dir holds node helpers like…

70k11d agoDiscuss
code-yeongyuAGENTS.md

oh-my-openagent / scripts

code-yeongyu/oh-my-openagent/scripts/AGENTS.md

Small Node ESM helpers that are intentionally separate from the primary Bun/TypeScript automation in singular script/. bun run test:codex invokes the --ship check after building the Codex payload. Release workflows…

70k11d agoDiscuss
code-yeongyuAGENTS.md

oh-my-openagent / tests

code-yeongyu/oh-my-openagent/tests/AGENTS.md

Cross-package invariants and integration fixtures that do not belong to one package's co-located unit suite.

70k11d agoReads credentialsDiscuss
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.