ecosystem-primer

1<overview>
2LangChain Inc. maintains three layered open-source tools for building agents, plus LangSmith for observability. The stack, top-down:
3 
4- **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.
5- **LangGraph** (middle layer, *runtime*) — low-level orchestration for durable execution, custom control flow, and stateful workflows. LangChain agents run on top of LangGraph.
6- **LangChain** (bottom layer, *framework*) — abstractions for models, tools, and the agent loop. Provider-agnostic, easiest to start with.
7- **LangSmith** (cross-cutting) — observability and evaluation platform. Framework-agnostic; always recommended alongside any of the above.
8 
9Higher 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.
10</overview>
11 
12---
13 
14## Step 1 — Choose Your Tool
15 
16<decision-table>
17 
18Evaluate these conditions in order and stop at the first match:
19 
201. If the task needs planning, file management across a long session, persistent memory, subagent delegation, or on-demand skills → **Deep Agents**
212. Else, if the task needs custom control flow (deterministic loops, branching logic) → **LangGraph**
22…