framework-selection

Framework selection guide for LangChain, LangGraph, and Deep Agents layered architecture. Picking a higher layer does not cut you off from lower layers — you can use LangGraph graphs inside Deep Agents, and LangChain primitives inside both. This skill should be loaded at the top of any project before selecting other skills or writing agent code. The framework you choose dictates which other skills to invoke next. Answer these questions in order: Best for: Not ideal when: Skills to invoke next: langchain-models , langchain-rag , langchain-middleware Best for: Not ideal when: Skills to invoke next: langgraph-fundamentals , langgraph-human-in-the-loop , langgraph-persistence Best for: Not ideal when: Middleware — built-in and extensible: Deep Agents ships with a built-in middleware layer out of the box — you configure it, you don't implement it. The following come pre-wired; you can also add your own on top: Skills to invoke next: deep-agents-core , deep-agents-memory , deep-agents-orchestration A LangGraph compiled graph can be registered as a subagent inside Deep Agents. This means you can build a tightly-controlled LangGraph workflow (e.g. a retrieval-and-verify loop) and hand it off to the Deep Agents task tool as a named subagent — the Deep Agents orchestrator delegates to it without caring about its internal graph structure. LangChain tools, chains, and retrievers can be...