Docs / Recipes / LangChain

// AGENT FRAMEWORK · LANGCHAIN

LangChain

Pattern A · full governance

Point ChatOpenAI at the gateway with one base_url. Every chain, agent, and tool call routes through Agentics.

Pattern A — routed through the gateway. Your call travels through Agentics via a base-URL swap, so it is governed (routing, budgets, guardrails) inline and the Proof Ledger writes one verifiable receipt server-side. The receipt hash comes back in the x-agentics-receipt response header.

Install

shell
pip install langchain-openai

Point the framework's OpenAI client at the gateway

langchain-openai also reads the OPENAI_BASE_URL environment variable.

Python
from langchain_openai import ChatOpenAI llm = ChatOpenAI( model="@anthropic/claude-opus-4-8", base_url="https://agentics.you/api/v1", # the only change api_key="ak_…", # AGENTICS_API_KEY default_headers={"x-agentics-user": "alice@acme.com"}, ) print(llm.invoke("hi").content)

You can also configure it via environment: OPENAI_BASE_URL=https://agentics.you/api/v1.

Run one call → see the receipt

Run your normal invocation, then read the receipt for that call off the ledger:

shell
# after your run, the last call's receipt hash: agentics log tail --limit 1 # → shows x-agentics-receipt: <receipt_hash> (verify it at /trust)

Every call the framework makes is now routed, governed, and receipted server-side.

Verify a receipt All recipes →