LangGraph integration

Action security for LangGraph.

Place action checks around graph nodes and tool nodes.

Get the Python SDK on PyPITry the local demoRead the documentation

Get the package and source.

Connect the execution boundary.

Wrap the agent and tool nodes that your application owns. A graph branch that calls a tool outside those wrappers needs a separate enforcement point.

An example to test

A claims graph retrieves a document that redirects a payment. Check the tool node with the final destination before advancing the workflow.

Illustrative workflow, not a customer deployment or a measured result.

Before connecting live policy

  1. Identify the handler that actually performs the side effect.
  2. Provide trusted identity, purpose and final action arguments.
  3. Configure the tenant’s assigned runtime and keep API credentials server-side.
  4. Test allowed, blocked and unavailable paths before production.

Integration example

Adapt this existing SDK pattern to your application. Names such as the agent, handler and session refer to your own objects. Follow the package documentation for compatible versions and complete setup.

# Install LangGraph support.
python -m pip install "agenticdome-python-sdk[langgraph]"

# Wrap existing graph nodes at the runtime boundaries you control.
from agenticdome_sdk.langgraph import AgenticDomeLangGraphFirewall

firewall = AgenticDomeLangGraphFirewall()
secure_agent_node = firewall.wrap_agent_node(existing_agent_node, agent_id="claims_agent")
secure_tool_node = firewall.wrap_tool_node(existing_tool_node, agent_id="claims_agent")

agenticdome-demo --framework langgraph --scenario refund_hijack

Python demo commands evaluate fixed inputs against a bundled local policy; they do not instantiate the selected framework or prove a live integration. The TypeScript client and OpenClaw runtime plugin need their documented tenant configuration.

Read the integration researchUnderstand runtime verification

See the decision before the action.

Try a local scenario, then bring your workflow to a deployment review. Start with one agent and one tool, and see exactly where the action can be stopped.

Try the local demo Book a deployment review