Skip to main content
Page stub. Full content lives in the README — LangChain / LangGraph.

​
TL;DR

from hexgate.adapters.langchain import wrap_langchain_agent
from hexgate.runtime import User

agent = wrap_langchain_agent(agent=graph, tools=TOOLS, api_key="sk-...")
result = await agent.ainvoke(
    {"messages": [{"role": "user", "content": "What is the weather in Tokyo?"}]},
    user=User(user_id="alice", role="member"),
)
Builds a PolicyEnforcer once and installs it on each tool in place so the same instances inside the compiled graph become policy-gated. Returns a HexgateLangchainAgent proxy that opens a User scope per call.