Comparisons / LangGraph vs OpenAI Agents SDK

LangGraph vs OpenAI Agents SDK: Which Agent Framework to Use?

LangGraph is LangChain's stateful workflow framework — a graph of nodes (functions) connected by edges with shared state. OpenAI's Agents SDK (evolved from Swarm) provides Agent, Runner, handoffs, and guardrails. Here is how they compare — paradigm, ecosystem, and the use cases each one is actually built for.

By the numbers

LangGraph

GitHub Stars

18.9k

Forks

3.4k

Language

Python

License

MIT

Created

2024-01-17

Created by

LangChain Inc (Harrison Chase)

Backed by

Sequoia Capital, Benchmark

Funding

Part of LangChain Inc — $50M raised across A and B

Weekly downloads

8.2M

Cloud/SaaS

LangGraph Platform (hosted), LangSmith (observability)

Production ready

Yes

Used by: Replit, Klarna, Elastic

github.com/langchain-ai/langgraph

OpenAI Agents SDK

GitHub Stars

20.6k

Forks

3.4k

Language

Python

License

MIT

Created

2025-03-11

Created by

OpenAI

github.com/openai/openai-agents-python

GitHub stats as of April 2026. Stars indicate community interest, not necessarily quality or fit for your use case.

ConceptLangGraphOpenAI Agents SDK
AgentA `StateGraph` with nodes, edges, and a typed `State` channel`Agent(name, instructions, model, tools)`
Tools`ToolNode(tools)` paired with a conditional edge for routingPython functions with type hints, auto-converted to schemas
Loop`add_conditional_edges` from a node back to itself until a `END` condition
StateTyped `State` channels with reducers (`Annotated[list, add_messages]`)
Checkpointing`MemorySaver` / `PostgresSaver` persists state per `thread_id`
Human-in-loop`interrupt_before` / `interrupt_after` pauses execution for review
Parallel fanoutMultiple edges from one node + reducers merge results
Agent Loop`Runner.run()` handles the loop internally
Handoffs`Handoff` between `Agent` objects for multi-agent routing
Guardrails`InputGuardrail` and `OutputGuardrail` with tripwire pattern
ContextTyped context object passed through the agent lifecycle

LangGraph vs OpenAI Agents SDK, head to head

LangGraph LangGraph is LangChain's stateful workflow framework — a graph of nodes (functions) connected by edges with shared state.

OpenAI Agents SDK OpenAI's Agents SDK (evolved from Swarm) provides Agent, Runner, handoffs, and guardrails.

Both wrap the same underlying agent pattern — an LLM call, a tool dispatch, a loop — in different abstractions. The choice between them is mostly about which mental model and ecosystem fits the team you have, not which one is technically more capable.

Pick LangGraph if

Pick LangGraph if langGraph earns its weight when your agent is a workflow — explicit branches, checkpoints, parallel branches, or a human approval gate. For a single-agent loop, the graph machinery is overkill and a plain while loop is faster to write, debug, and ship. LangGraph is the right fit when the tradeoffs in its intro line up with how your team actually wants to work day-to-day; OpenAI Agents SDK would force you to translate.

Full LangGraphcomparison →

Pick OpenAI Agents SDK if

Pick OpenAI Agents SDK if the Agents SDK is the thinnest framework on this list — it barely abstracts beyond what you'd write yourself. Use it when you want OpenAI's conventions and auto-schema generation. Skip it when you want full control or use non-OpenAI models. OpenAI Agents SDK is the right fit when the tradeoffs in its intro line up with how your team actually wants to work day-to-day; LangGraph would force you to translate.

Full OpenAI Agents SDKcomparison →

What both add

Both LangGraph and OpenAI Agents SDK pull in a class hierarchy and a dependency tree to wrap what is, at the core, an HTTP POST in a while loop. If your use case is straightforward — one provider, a handful of tools, a single agent — the framework cost may exceed the framework benefit. The lesson below shows the same pattern in ~60 lines without either dependency.

Or build your own in 60 lines

Both LangGraph and OpenAI Agents SDK implement the same 8 patterns. An agent is a function. Tools are a dict. The loop is a while loop. The whole thing composes in ~60 lines of Python.

No framework. No dependencies. No opinions. Just the code.

Build it from scratch →