LangChain Ecosystem Router

Framework Selection

Frameworks are layered, not competing:

┌─────────────────────────────────────┐
│         Deep Agents                 │  ← planning, memory, skills, files
├─────────────────────────────────────┤
│          LangGraph                  │  ← graphs, loops, state, control flow
├─────────────────────────────────────┤
│         LangChain                   │  ← models, tools, prompts, RAG
└─────────────────────────────────────┘

Decision tree (answer in order):

1. Needs sub-tasks, file management, persistent memory, or on-demand skills? → Deep Agents
2. Needs complex control flow (loops, branching, parallel, human-in-the-loop)? → LangGraph
3. Single-purpose agent with fixed tools? → LangChain (create_agent)
4. Pure model call, chain, or retrieval pipeline? → LangChain (LCEL)

LangChain tools/chains/retrievers work inside LangGraph nodes and Deep Agents tools. LangGraph compiled graphs can be registered as Deep Agents subagents.

Quick Start (Most Common Patterns)

Simple agent:

from langchain.agents import create_agent
agent = create_agent(model="anthropic:claude-sonnet-4-5", tools=[my_tool])
result = agent.invoke({"messages": [{"role": "user", "content": "Hello"}]})
print(result["messages"][-1].content)

Stateful graph:

from langgraph.graph import StateGraph, START, END
graph = StateGraph(State).add_node("process", fn).add_edge(START, "process").add_edge("process", END).compile()

Deep Agent:

from deepagents import create_deep_agent
agent = create_deep_agent(model="claude-sonnet-4-5-20250929", tools=[my_tool], system_prompt="...")

Critical Rules (All Frameworks)

• Persistence always needs thread_id: config = {"configurable": {"thread_id": "..."}}
• HITL always needs checkpointer: MemorySaver() at minimum
• Resume after interrupt: Command(resume={"decisions": [{"type": "approve"}]}) — never plain dict
• LangChain 1.0 is LTS — never start new projects on 0.3
• Always install langchain-core explicitly — not auto-hoisted in monorepos
• Use dedicated packages (e.g., langchain-chroma) not langchain_community

Deep-Dive References

LangChain

LangGraph

Deep Agents

Meta