Skip to main content

AutoGen Integration

Use KoreShield as a proxy for AutoGen agent requests to enforce sanitization, detection, and policy controls before traffic reaches your provider.

Use Cases​

  • Multi-agent workflows with strict safety policies
  • Centralized auditing for agent traffic
  • Shared rate limiting across agent fleets

Prerequisites​

  • A running KoreShield instance
  • Provider API key configured on the KoreShield server
  • AutoGen installed in your Python app

Environment Variables​

KORESHIELD_BASE_URL=http://localhost:8000
KORESHIELD_API_KEY=your-koreshield-api-key

Example: AutoGen Agents with KoreShield​

import autogen

llm_config = {
    "config_list": [
        {
            "model": "gpt-4o",
            "api_key": "unused",
            "base_url": "http://localhost:8000",
            "default_headers": {
                "Authorization": "Bearer your-koreshield-api-key"
            }
        }
    ],
    "temperature": 0.2
}

assistant = autogen.AssistantAgent(
    name="assistant",
    llm_config=llm_config
)

user_proxy = autogen.UserProxyAgent(
    name="user",
    human_input_mode="NEVER",
    max_consecutive_auto_reply=3
)

user_proxy.initiate_chat(
    assistant,
    message="Summarize the incident report and flag risky items."
)

Security Notes​

  • Keep provider API keys on the KoreShield server.
  • Use a Koreshield API key for client access when needed.
  • Tune policies in /configuration/.

Troubleshooting​

  • 401 responses: confirm Authorization: Bearer <JWT_TOKEN> or X-API-Key: <API_KEY>
  • Agent errors: confirm AutoGen uses the proxy base_url
  • Provider failures: verify provider keys on the KoreShield server

Next Steps​