Nyraxis AI
FeaturesHow it worksIntegrationsPricingDocs
Get started
← Integration guides

LangChain Integration

Add full observability and governance to your LangChain agents in under 2 minutes.

Install

pip install nyraxis-sdk

Quick start

from nyraxis_sdk import LangChainCallbackHandler
from langchain_openai import ChatOpenAI

handler = LangChainCallbackHandler(
    api_key="nyx_your_api_key",
    base_url="http://localhost:8000",  # or your Nyraxis cloud URL
    agent_name="my-langchain-agent",
)

llm = ChatOpenAI(model="gpt-4o", callbacks=[handler])
response = llm.invoke("Summarize the latest AI news")

await handler.flush()  # send trace to Nyraxis

What gets captured

  • Every LLM call — model, prompt, completion, token counts, latency
  • Tool calls — name, parameters, result
  • Cost auto-calculated from token counts + model pricing table
  • Governance policies evaluated in real-time (PII, prompt injection, cost limits)

With LCEL chains

from langchain_core.prompts import ChatPromptTemplate

chain = ChatPromptTemplate.from_template("{topic}") | llm
result = chain.invoke({"topic": "AI governance"}, config={"callbacks": [handler]})
await handler.flush()

With LangGraph agents

from langgraph.prebuilt import create_react_agent

agent = create_react_agent(llm, tools=[...])
result = agent.invoke({"messages": [...]}, config={"callbacks": [handler]})
await handler.flush()

View traces at /dashboard/traces in your Nyraxis dashboard.

Other integrations