A fixed path
A pipeline with a known order. langchain.com barely mentions this anymore, but it is still the right tool when you already know the steps.
LangChain, LangGraph, Deep Agents, LangSmith
The same job, four runtimes.
Take one job and run it as a chain, a LangChain agent, a Deep Agent, or a LangGraph. See where each one fits, and where it stops.
The stack
Deep Agents sits on LangChain. Both sit on LangGraph. LangSmith is how you watch a run.
Select a layer. The description stays until you pick another.
create_deep_agent adds a filesystem, skills, subagents, and planning on top of the agent loop.
The open-source stack
Four ways to run the same work.
create_agent
LangChain's create_agent: a model in a loop with tools. Built on LangGraph, without making you draw the graph.
create_deep_agent
Deep Agents: the same loop, plus a filesystem, skills, subagents, and planning, already wired up.
LangGraph
LangGraph is the runtime underneath: durable runs, streaming, human-in-the-loop. Learn LangGraph is the graph practice.
The comparison
LangChain vs LangGraph vs Deep Agents
Not rivals — layers. Pick by the shape of the job, not the name on the box.
| Chain | create_agent | Deep Agents | LangGraph | |
|---|---|---|---|---|
| The shape | A fixed path | A loop | A harness on the loop | A graph you draw |
| Who picks the next step | You, in advance | The model | The model, with a plan | Your edges |
| Work that comes back | Never | Retries until tools settle | Long tasks, subagents | Cycles you define |
| Waiting for a person | No | Middleware | Via the graph underneath | Interrupts and checkpoints |
| Reach for it when | Steps are known | One job, some tools | Research, coding sessions | Approvals, branches, multi-agent |
Where to start
Open the studio, or read the jobs first.
Glossary
What these words mean here
LangChain's site uses these as product names. Here they are just the machines.
- Chain
- A pipeline. You already know the steps and the order. langchain.com barely talks about this now; it is still the right tool for a one-pager.
- LangChain
- create_agent: a model in a loop with tools. The framework. You do not have to draw a graph to start.
- Deep Agents
- create_deep_agent: that same loop, plus a filesystem, skills, subagents, and planning, already attached.
- LangGraph
- The runtime underneath. Durable runs, streaming, human-in-the-loop. You draw the graph when the loop is not the right shape. Practice that in Learn LangGraph. Open Learn LangGraph
- LangSmith
- Traces, evals, and deploy. How you watch a run after it leaves your laptop.
- Agent Server
- LangSmith's host for an agent: endpoints, sandboxes, a place for a schedule.
- Fleet
- The no-code builder. For people who are not going to open a repo.
- Engine
- Groups similar production failures and can suggest a fix. You still have to accept it.
- LLM Gateway
- Sits in front of the models: spend caps, PII, routing.
FAQ
Six questions
Do I need an API key?
No. The studio is simulated. Nothing calls a model.
Is this official LangChain?
No. A community resource from En Dash. The product names are real; the runs are not.
When is a chain enough?
When the steps are known and the work never comes back. The PDF one-pager is a chain. The rental that waits for a person is a graph.
LangChain vs LangGraph — which should I use?
They are layers, not rivals. LangChain is the framework: integrations, tools, create_agent. LangGraph is the runtime it runs on. Start with create_agent; write LangGraph directly when the job needs branches, pauses, or state you can replay.
Is LangGraph replacing LangChain?
No. create_agent runs on the LangGraph engine, so every LangChain agent is already a small graph. Dropping to LangGraph syntax just means drawing the loop yourself.
What are Deep Agents?
A harness on top of the agent loop: planning, a filesystem, subagents. The architecture behind tools like Claude Code and deep research. Overkill for a Tuesday ticket; right for work that runs long enough to need a plan.