It answers two questions that every project must resolve upfront:

1. Which framework should I use? — LangChain, LangGraph, or Deep Agents
2. What do I need to install? — packages, versions, and environment setup

Load this skill first. Once you’ve made these decisions, invoke the framework-specific skill for implementation details.

Step 1 — Pick Your Framework

The three frameworks are layered, not competing. Each builds on the one below:

┌─────────────────────────────────────────┐
│              Deep Agents                │  ← batteries included
│   (planning, memory, skills, files)     │
├─────────────────────────────────────────┤
│               LangGraph                 │  ← custom orchestration
│    (nodes, edges, state, persistence)   │
├─────────────────────────────────────────┤
│               LangChain                 │  ← foundation
│      (models, tools, prompts, RAG)      │
└─────────────────────────────────────────┘

Answer these questions in order to land on the right choice:

Higher layers depend on lower ones only when necessary — which means you can mix them. A LangGraph graph can be a subagent inside Deep Agents; LangChain tools work inside both.

Middleware is a concept specific to LangChain (callbacks) and Deep Agents (explicit middleware layer). LangGraph has no middleware — behavior is wired directly into nodes and edges. If a user asks for built in hooks, route to LangChain or DeepAgents

Deep Agents built-in middleware

Deep Agents ships with a built-in middleware layer — six components pre-wired out of the box, with the ability to add your own. The first three are always active; the rest are opt-in via configuration:

You configure middleware — you don’t implement it. See deep-agents-core for setup details.

Step 2 — Set Up Your Dependencies

Environment requirements

Always use LangChain 1.0+. LangChain 0.3 is maintenance-only until December 2026 — do not start new projects on it.

Core packages — always required

Orchestration — add based on your framework choice

Model providers — pick the one(s) you use

Common tools & retrieval — add as needed

Prefer dedicated integration packages over langchain-community when one exists — they are independently versioned and more stable. Keep tool packages (Tavily, vector stores) at latest since they release compatibility fixes alongside core updates.

Dependency templates

Add your model provider:

langchain-openai | langchain-anthropic | langchain-google-genai | …

Add tools/retrieval as needed:

langchain-tavily | langchain-chroma | langchain-text-splitters | …

</python>
</ex-langgraph-python>

<ex-langgraph-typescript>
<typescript>
LangGraph project — provider-agnostic starting point.
```json
{
  "dependencies": {
    "@langchain/core": "^1.0.0",
    "langchain": "^1.0.0",
    "@langchain/langgraph": "^1.0.0",
    "langsmith": "^0.1.99"
  }
}

Add your model provider:

langchain-openai | langchain-anthropic | langchain-google-genai | …

</python>
</ex-deepagents-python>

<ex-deepagents-typescript>
<typescript>
Deep Agents project — provider-agnostic starting point.
```json
{
  "dependencies": {
    "deepagents": "latest",
    "@langchain/core": "^1.0.0",
    "langchain": "^1.0.0",
    "langsmith": "^0.1.99"
  }
}

Step 3 — Set Your Environment Variables

Model provider — set the one(s) you use

OPENAI_API_KEY= ANTHROPIC_API_KEY= GOOGLE_API_KEY= MISTRAL_API_KEY= GROQ_API_KEY= COHERE_API_KEY= FIREWORKS_API_KEY= TOGETHER_API_KEY= HUGGINGFACEHUB_API_TOKEN=

Common tool/retrieval services

TAVILY_API_KEY= PINECONE_API_KEY=

</environment-variables>

---

## Step 4 — Load the Right Skill Next To Dive Deeper