Connect a LangChain Agent - GroundForge

Create the Agent normally, then initialize GroundForge once after the Agent is constructed.

import os
from groundforge_langchain import init as init_groundforge

runtime = init_groundforge(
    agent=agent,
    endpoint="https://platform.groundforge.ai",
    api_key=os.environ["GROUNDFORGE_API_KEY"],
    agent_id=os.environ["GROUNDFORGE_AGENT_ID"],
    tenant_id=os.environ["GROUNDFORGE_TENANT_ID"],
    workspace_id=os.environ["GROUNDFORGE_WORKSPACE_ID"],
    name="Weather Agent",
    execution_mode="managed_intake",
    serve=False,
)

Continue using the Agent as before:

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What is the weather in Ottawa?"}]}
)

No custom caller metadata is required. GroundForge creates one Trace for the invocation and instruments supported model and tool activity. Use Service Mode when Channels should dispatch requests to the running process.

Example

groundforgeai/demo

Follow the full setup in LangChain Agent Example.

Last modified on July 27, 2026