Microsoft AutoGen integration

Action security for Microsoft AutoGen.

Carry action context through multi-agent team execution.

Get the Python SDK on PyPITry the local demoRead the documentation

Get the package and source.

Connect the execution boundary.

Wrap the team and verify the tool paths used by participating agents. A team wrapper is not a substitute for testing the final executor.

An example to test

A research agent passes poisoned instructions to a billing agent. Retain the original purpose when evaluating the proposed refund.

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 current Microsoft AutoGen support.
python -m pip install "agenticdome-python-sdk[autogen]"

from autogen_agentchat.teams import RoundRobinGroupChat
from agenticdome_sdk.autogen import AgenticDomeAutoGenFirewall

firewall = AgenticDomeAutoGenFirewall()
team = RoundRobinGroupChat([research_agent, billing_agent], max_turns=12)
protected_team = firewall.wrap_team(team, session_id="sess_prod_01J4X", agent_id="autogen_group_chat")
result = await protected_team.run(task="Resolve the approved support case")

# Prove cross-agent poisoning is blocked before the tool executes.
agenticdome-demo --framework autogen --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