create_agent: a minimal, highly configurable harness. The harness is everything around the model loop: the prompt, the tools, and any middleware that shapes behavior. Start with the primitives and compose exactly what your use case needs. Supports OpenAI, Anthropic, Google, and more.
LangChain vs. LangGraph vs. Deep AgentsStart with Deep Agents for a “batteries-included” agent with features like automatic context compression, a virtual filesystem, and subagent-spawning. Deep Agents are built on LangChain agents which you can also use directly.Use LangChain (
create_agent) for a highly customizable harness, easily tailored to your use case and data.Use LangGraph, our low-level orchestration framework, for advanced needs combining deterministic and agentic workflows.Use LangSmith to trace, debug, and evaluate agents built with any of these frameworks. Follow the tracing quickstart to get set up. We recommend you also set up LangSmith Engine which monitors your traces, detects issues, and proposes fixes.Create an agent
This example demonstrates how to create a simple LangChain agent with a custom tool:# pip install -qU langchain "langchain[openai]"
from langchain.agents import create_agent
def get_weather(city: str) -> str:
"""Get weather for a given city."""
return f"It's always sunny in {city}!"
agent = create_agent(
model="openai:gpt-5.5",
tools=[get_weather],
system_prompt="You are a helpful assistant",
)
result = agent.invoke(
{"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
Use LangSmith to trace requests, debug agent behavior, and evaluate outputs. Set
LANGSMITH_TRACING=true and your API key to get started.Core benefits
Standard model interface
Use one interface for chat models, embeddings, and more across providers. Switch models with minimal code changes and keep your application portable as requirements evolve.
Highly configurable harness
Start with
create_agent as a minimal harness and add capabilities incrementally through middleware. Compose only what your use case needs, from guardrails and retries to routing and custom tool policies.
Built on top of LangGraph
LangChain’s agents are built on top of LangGraph. This allows us to take advantage of LangGraph’s durable execution, human-in-the-loop support, persistence, and more.
Debug with LangSmith
Inspect traces, tool calls, state transitions, and latency in one place. Find failure modes, evaluate quality, and improve agent behavior with execution data.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.