LangChain

Auto-trace chain, LLM, and tool lifecycle events from LangChain and LangGraph.

Installation

pip install "axonpush[langchain]"

Setup

import os
from axonpush import AxonPush
from axonpush.integrations.langchain import AxonPushCallbackHandler

client = AxonPush(
    api_key=os.environ["AXONPUSH_API_KEY"],
    tenant_id=os.environ["AXONPUSH_TENANT_ID"],
    base_url=os.environ.get("AXONPUSH_BASE_URL", "https://api.axonpush.xyz"),
)

handler = AxonPushCallbackHandler(
    client=client,
    channel_id=1,
    agent_id="langchain-agent",
)

Usage

Pass the handler via config to any chain or agent:

result = chain.invoke(input, config={"callbacks": [handler]})

result = agent_executor.invoke(
    {"input": "What are AI agents?"},
    config={"callbacks": [handler]},
)

Events Traced

Event	When
chain.start	Chain begins execution
chain.end	Chain completes
llm.start	LLM call begins
llm.end	LLM call completes
tool.*.start	Tool execution begins
tool.end	Tool execution completes