OpenAI Agents SDK integration

Action security for OpenAI Agents SDK.

Add an independent policy decision to agent runs and tools.

Get the Python SDK on PyPITry the local demoRead the documentation

Get the package and source.

Connect the execution boundary.

Use the secure runner around the application-owned execution path. Check handoffs and final tool invocations separately when they bypass that path.

An example to test

A service agent is steered into exporting customer metadata. Compare the action with the user’s purpose and authorised destination before execution.

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 OpenAI Agents SDK support.
python -m pip install "agenticdome-python-sdk[openai-agents]"

from agenticdome_sdk.openai_agents import AgenticDomeOpenAIAgentsFirewall

firewall = AgenticDomeOpenAIAgentsFirewall()
result = await firewall.run_agent_securely(
    runner=runner, agent=support_agent, input_text=user_prompt, session_id=session_id
)

agenticdome-demo --framework openai-agents --scenario metadata_exfil

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