Ecosystem Primer

This is the required entry point before writing any LangChain, LangGraph, or Deep Agents code. It walks you through picking the right layer (Deep Agents for planning and memory, LangGraph for custom control flow, plain LangChain for single-purpose agents), sets up LangSmith tracing with the current env var names, and tells you exactly which skill to load next based on your choice. The decision table is terse and opinionated, which is what you want when the ecosystem has three overlapping tools. Load this first, follow the steps, then jump to the layer-specific skill. Skipping it means you'll probably pick the wrong abstraction or use outdated API calls.

skills.sh installs: 8.8K
GitHub stars: 1.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add langchain-ai/langchain-skills --skill ecosystem-primer --agent claude-code

Installs into .claude/skills of the current project.

Files

LangChain Inc. maintains three layered open-source tools for building agents, plus LangSmith for observability. The stack, top-down:

Deep Agents (top layer, harness) — batteries-included toolkit built on LangChain + LangGraph. Ships with planning, file management, subagent spawning, and memory out of the box.
LangGraph (middle layer, runtime) — low-level orchestration for durable execution, custom control flow, and stateful workflows. LangChain agents run on top of LangGraph.
LangChain (bottom layer, framework) — abstractions for models, tools, and the agent loop. Provider-agnostic, easiest to start with.
LangSmith (cross-cutting) — observability and evaluation platform. Framework-agnostic; always recommended alongside any of the above.

Higher layers depend on lower ones, but you don't need to use lower layers directly. Deep Agents gives you LangGraph's durable execution without writing graph code. LangChain gives you models and tools without managing graph edges.