This document provides guidelines for AI agents (e.g., GitHub Copilot, MCP-based assistants, LLM-based tools) working with the Azure SDK for .NET repository. It defines safe and effective patterns for agent interactions with this codebase, automation workflows, and development processes. The Azure SDK for .NET repository contains: - Data plane client Libraries: SDKs for interacting with Azure services at application runtime - Management plane Libraries: SDKs for provisioning and managing Azure resources - Code Generators: Tools that generate Azure Data Plane…
This is a LangChain project, not an ADK one: app/agent.py compiles a LangGraph graph and app/fastapiapp.py serves it over A2A. Read .agents/skills/agents-cli-langchain/SKILL.md before changing either. Experimental. Cloud Run and GKE are the supported targets. On Agent Runtime the container serves and traces normally, but everything that expects an ADK app is broken, because this project serves A2A and no reasoning_engine routes: - agents-cli publish gemini-enterprise is refused: registration invokes the agent through :streamQuery. Publish from a Cloud Run or GKE…
Alloy is a code generation framework using JSX components. Before working with Alloy code, read the relevant docs from installed packages. Your training data may be outdated — these docs match your installed version.
This file provides guidance for AI coding agents working in this repository. This is a living document. When you make a mistake or learn something new about this codebase, add it to Lessons Learned. Authentication uses Better Auth with Vercel OAuth (sign-in) and GitHub OAuth (repo access). Config lives in apps/web/lib/auth/config.ts. Sessions are managed by better-auth's built-in session system — there is no manual JWE/encryption layer. Key env vars: BETTERAUTHSECRET (session signing), NEXTPUBLICVERCELAPPCLIENTID + VERCELAPPCLIENTSECRET (Vercel OAuth), plus GitHub App…
Version 1.0.0 Vercel Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React and Next.js codebases. Humans may also find it useful, but guidance here is optimized for automation and consistency by AI-assisted workflows. Comprehensive performance optimization guide for React and Next.js applications, designed for AI agents and LLMs. Contains 40+ rules across 8 categories, prioritized by impact from critical (eliminating waterfalls, reducing bundle size) to incremental (advanced patterns). Each…
Cloudflare Agents SDK — a framework for building stateful AI agents on Cloudflare Workers. This is a monorepo containing the core SDK packages, examples, guides, sites, and documentation. Some directories have their own AGENTS.md with deeper guidance: Node 24+ required. Uses pnpm workspaces with Nx for task orchestration, caching, and affected detection. Run from the repo root: Run an exampl
A Think agent (@cloudflare/think) that reproduces and fixes cloudflare/agents GitHub issues inside a container-backed @cloudflare/workspace VFS. Anyone trusted on the repo triggers it from an issue comment: e.g. @agent-think reproduce this issue or @agent-think open a PR fixing this. It runs the matching skill (reproduce / open-pr) in a real Linux container and reports back on the issue as the agent-think GitHub App — never impersonating the triggering user. - Replace CI-runner automations (the /repro + /pr Actions shape from…
Internal design records — the "why" behind decisions in this repo and its libraries. This is the Diátaxis explanation quadrant: architecture rationale, tradeoffs, and alternatives considered. Living documents that describe how a concept or subsystem works right now. Named by topic: state.md, mcp.md, visuals.md. These are the primary entry point — a contributor looking for "how does state work" should open one file and get the full picture. Design docs get updated as the implementation evolves. They always reflect the…
User-facing documentation for the Agents SDK monorepo. Each package owns the directory under docs/ matching its unscoped package name. These markdown files are manually synced to developers.cloudflare.com/agents/ where applicable. We follow Diátaxis to keep docs focused. Every doc should have a clear primary type: The fourth Diátaxis type — explanation ("understand why") — lives in /design, not here. If you're writing about why something was designed a certain way, put it there. If you're writing about how to use something,…
Self-contained demo apps that show how to use the Agents SDK. These are user-facing learning material — keep them simple, clear, and consistent. Each example should focus on one feature or concept (e.g., MCP servers, email routing, workflows). The exception is playground/, which is the kitchen-sink showcase covering the full spread of SDK features in a single app. Most examples have both a frontend and a backend. This makes them immediately runnable and visually demonstrable — users can pnpm run…
In-depth, pattern-oriented tutorials — runnable apps with substantial narrative READMEs that teach how to build a particular kind of agent application. If it demonstrates a single feature, it belongs in /examples. If it teaches an approach or pattern, it belongs here. Guides are runnable apps with the same structural conventions as examples: The README is the guide. The code is the supporting material. A guide README should walk a reader through the application, explaining both what the code does and…
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo. Each export maps to a public entry point that users import from. These are the boundaries of the public API — changes here need a changeset.
Harness Durable Objects for testing Lifecycle capabilities — the lower-level sibling of ../agents/ (which holds Agent-level fixture classes). One file per capability, all registered in the shared workers project (../worker.ts + ../wrangler.jsonc), all driving real Durable Objects. - harness.ts — the generic tier's bare CapabilityHarnessObject. Its driver, withCapabilityHarness() (in ../shared/capability-harness.ts), binds per-test-constructed capabilities to a real Lifecycle over real SQLite storage — a new capability gets isolation tests with zero new wiring. - lifecycle.ts — fixtures for the Lifecycle core…
This file describes how AI agents (e.g., GitHub Copilot, MCP servers, or LLM-based assistants) should interact with this repository. Purpose: This repository contains the active development of the Azure SDK for Python, providing client libraries and management libraries for Azure services. Scope: - 100+ Python packages for Azure services - Client libraries for data plane operations - Management libraries for Azure Resource Manager (ARM) - Shared core functionality (authentication, retries, logging, transport) - TypeSpec-based SDK generation from API specifications -…
This document provides instructions for agents on how to perform common development tasks in this repository. This project uses asdf to manage tool versions. Before you can install the project's dependencies, you need to install and configure asdf. First, make sure you have git and curl installed. Then, clone the asdf repository: Add asdf to your shell's startup file. For bash, run: Then, source your .bashrc to apply the changes to your current session: Now, from the root of this…
This is the only agent guide for the repository. Its rules apply everywhere, including docs/ and internal/compatibility/. Write prose paragraphs and list items as single source lines and let editors and renderers wrap them naturally. Do not hard-wrap Markdown at a fixed column; preserve separate lines only where Markdown syntax or intentional formatting requires them, such as headings, lists, tables, blockquotes, and code blocks. The ordinary workspace build does not rebuild packaged native artifacts. When changing native assembly/object emission or…
Guidance for coding agents (and humans) working in this repository. For setup, PR workflow, and release process, see CONTRIBUTING.md. eve is a filesystem-first framework for durable backend AI agents. You author an agent as a directory on disk — instructions, skills, tools, connections, channels, subagents, and schedules are all files — and eve compiles and runs it. See the README for the full overview and docs/ for user-facing documentation. Always style the framework name as eve, lowercase, in user-facing copy,…
All user-facing UI changes must be mobile-responsive. Before completing a UI change, verify it at a narrow mobile viewport and a desktop viewport. Check for page-level horizontal overflow, clipped content, unreadably narrow columns, overlapping controls, and whether dense navigation should wrap or scroll horizontally. This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not…
This project uses the eve framework. Before writing code, always read the relevant guide in node_modules/eve/dist/docs/public/. Use eve lowercase in user-facing copy, docs, prompts, and comments. Do not title-case it unless it is part of an exact external title or quoted text.
Microsoft AzureAGENTS.md
