Azure OpenAI + Govyn — Govern Your Azure AI Agents

Azure OpenAI gives you enterprise-grade infrastructure, but it doesn't provide per-agent budget controls or policy enforcement. When multiple teams deploy agents against shared Azure endpoints, you need a governance layer to prevent cost overruns and ensure compliance.

How it works

Azure OpenAI
Your agents
─ HTTPS →
Govyn Proxy
Policy · Budget · Logs
─ API →
Azure OpenAI API
LLM provider

Step-by-step setup

1

Start the Govyn proxy with Azure routing

bash 
npx govyn start --config govyn.yaml
2

Configure Govyn for Azure OpenAI

yaml 
# govyn.yaml
routing:
  azure:
    upstream: https://your-resource.openai.azure.com
    headers:
      api-key: ${AZURE_OPENAI_KEY}
    format: azure-openai
3

Point your agent at Govyn

python 
from openai import AzureOpenAI

client = AzureOpenAI(
    azure_endpoint="http://localhost:4111",
    api_key="gvn_agent_azure_01",
    api_version="2024-06-01"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Analyze this report"}]
)

Example policy

Define governance rules for your Azure OpenAI agents in a simple YAML file.

govyn.yaml 
routing:
  azure:
    upstream: https://your-resource.openai.azure.com
    headers:
      api-key: ${AZURE_OPENAI_KEY}
    format: azure-openai

agents:
  azure_01:
    budget:
      daily: $20.00
      monthly: $500.00
    models:
      allow: [gpt-4o, gpt-4o-mini]
    rate_limit:
      requests_per_minute: 50
    logging:
      replay: true
      redact_pii: true
      retention_days: 90

Why use Govyn with Azure OpenAI?

Per-agent budgets on shared Azure deployments
Model and deployment restrictions
PII redaction for compliance logging
Configurable log retention periods
Rate limiting per agent and team
Works with Azure AD authentication

Get started in 5 minutes

Add governance to your Azure OpenAI agents with a single config change. No code rewrites.

Read the docs

Frequently asked questions

Does Govyn work with Azure OpenAI's API format?
Yes. Govyn natively supports Azure OpenAI's API format, including deployment-based routing and API versioning. Configure your Azure endpoint in the routing section and Govyn handles the format translation.
Can I use Govyn alongside Azure's built-in content filtering?
Yes. Govyn operates at the proxy level before requests reach Azure. Azure's content filtering still runs on the Azure side. You get Govyn's budget and policy controls plus Azure's content safety — they're complementary layers.
How does Govyn help with enterprise compliance on Azure?
Govyn adds per-agent audit trails, PII redaction, configurable log retention, and policy enforcement. Combined with Azure's enterprise infrastructure, you get a complete governance stack for regulated industries.

Related integrations

LangChain + OpenAI

Add budget limits, policy enforcement, and full replay to LangChain agents using OpenAI. Five-minute setup, zero code changes.
Ollama

Govern local LLM agents running on Ollama. Enforce model policies, rate limits, and full audit trails for self-hosted models.
OpenAI Agents SDK + OpenAI

Add governance to OpenAI Agents SDK. Enforce budgets, model policies, and audit trails for every agent run. Five-minute setup.

Explore more

FROM OUR BLOG
We Cut Our AI API Bill by 73% Without Changing a Single Line of Agent Code

How smart model routing through a proxy cut our OpenAI and Anthropic bill from $2,140/mo to $578/mo. Zero code changes. Just YAML.

POLICY TEMPLATE
Budget Control Policy

Set daily and monthly spending limits for AI agents. Prevent runaway costs with hard budget caps enforced at the proxy level.

POLICY TEMPLATE
Compliance Audit Policy

Maintain complete audit trails for AI agent operations. Log every request, response, and policy decision for regulatory compliance.

COMPARISON
Govyn vs Coralogix

Compare Govyn and Coralogix for AI agent governance. Proxy-level enforcement vs enterprise observability with AI monitoring.