> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# OpenAI Agents SDK (TypeScript)
> Use Prisma AIRS AI Gateway with OpenAI Agents SDK to take your AI Agents to production
## Introduction
OpenAI Agents SDK enables the development of complex AI agents with tools, planning, and memory capabilities. The AI Gateway enhances OpenAI Agents with observability, reliability, and production-readiness features.
The AI Gateway turns your experimental OpenAI Agents into production-ready systems by providing:
* **Complete observability** of every agent step, tool use, and interaction
* **Built-in reliability** with fallbacks, retries, and load balancing
* **Cost tracking and optimization** to manage your AI spend
* **Access to 3,000+ LLMs** through a single integration
* **Guardrails** to keep agent behavior safe and compliant
* **Version-controlled prompts** for consistent agent performance
Learn more about OpenAI Agents SDK's core concepts
### Installation & Setup
```bash theme={"system"}
npm install @openai/agents
```
Create an AI Gateway API key with optional budget/rate limits and attach your Config
There are 3 ways to integrate the AI Gateway with OpenAI Agents:
1. Set a client that applies to all agents in your application
2. Use a custom provider for selective AI Gateway integration
3. Configure each agent individually
See the [Integration Approaches](#integration-approaches) section for more details.
For a simple setup, we'll use the global client approach:
```typescript theme={"system"}
import { Agent, run } from '@openai/agents';
import { setDefaultOpenAIClient, setOpenAIAPI, setTracingDisabled } from '@openai/agents';
import { OpenAI } from 'openai';
// Set up the AI Gateway as the global client
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: { "x-portkey-provider": "@YOUR_OPENAI_PROVIDER" }
});
// Register as the SDK-wide default
setDefaultOpenAIClient(gateway);
setOpenAIAPI('chat_completions'); // Responses API → Chat
setTracingDisabled(true); // Optional: disable OpenAI's tracing
```
### Getting Started
Let's create a simple question-answering agent with OpenAI Agents SDK and the AI Gateway. This agent will respond directly to user messages using a language model:
```typescript theme={"system"}
import { Agent, run } from '@openai/agents';
import { setDefaultOpenAIClient, setOpenAIAPI, setTracingDisabled } from '@openai/agents';
import { OpenAI } from 'openai';
// Set up the AI Gateway as the global client
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!
});
// Register as the SDK-wide default
setDefaultOpenAIClient(gateway);
setOpenAIAPI('chat_completions'); // Responses API → Chat
setTracingDisabled(true); // Optional: disable OpenAI's tracing
// Create agent with any supported model
const agent = new Agent({
name: "Assistant",
instructions: "You are a helpful assistant.",
model: "@YOUR_OPENAI_PROVIDER/gpt-4o"
});
// Run the agent
const result = await run(agent, "Tell me about quantum computing.");
console.log(result.finalOutput);
```
In this example:
1. We set up the AI Gateway as the global client for OpenAI Agents SDK
2. We create a simple agent with instructions and a model
3. We run the agent with a user query
4. We print the final output
Visit Strata Cloud Manager to see detailed logs of this agent's execution!
## End-to-End Example
**Research Agent with Tools**: Here's a more comprehensive agent that can use tools to perform tasks.
```typescript [expandable] theme={"system"}
import { Agent, run, tool } from '@openai/agents';
import { setDefaultOpenAIClient } from '@openai/agents';
import { OpenAI } from 'openai';
import { z } from 'zod';
// Configure the AI Gateway client
const gateway = new OpenAI({
apiKey: process.env.PORTKEY_API_KEY!,
baseURL: "https://aigw.portkey.ai/v1"
});
setDefaultOpenAIClient(gateway);
// Define agent tools using the tool() helper
const getWeatherTool = tool({
name: 'get_weather',
description: 'Get the current weather for a given city',
parameters: z.object({
city: z.string(),
unit: z.enum(['celsius', 'fahrenheit']).nullable().optional()
}),
async execute({ city, unit = 'fahrenheit' }) {
return `The weather in ${city} is 72°${unit === 'celsius' ? 'C' : 'F'} and sunny.`;
}
});
const searchWebTool = tool({
name: 'search_web',
description: 'Search the web for information',
parameters: z.object({
query: z.string()
}),
async execute({ query }) {
return `Found information about: ${query}`;
}
});
// Create agent with tools
const agent = new Agent({
name: "Research Assistant",
instructions: "You are a helpful assistant that can search for information and check the weather.",
model: "@YOUR_OPENAI_PROVIDER/gpt-4o",
tools: [getWeatherTool, searchWebTool]
});
// Run the agent
const result = await run(
agent,
"What's the weather in San Francisco and find information about Golden Gate Bridge?"
);
console.log(result.finalOutput);
```
Visit Strata Cloud Manager to see the complete execution flow visualized!
***
## Production Features
### 1. Enhanced Observability
The AI Gateway provides comprehensive observability for your OpenAI Agents, helping you understand exactly what's happening during each execution.
Traces provide a hierarchical view of your agent's execution, showing the sequence of LLM calls, tool invocations, and state transitions.
```typescript theme={"system"}
// Add tracing to your OpenAI Agents
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: {
"x-portkey-provider": "@YOUR_OPENAI_PROVIDER",
// Add unique trace ID
"x-portkey-trace-id": "unique_execution_trace_id",
}
});
setDefaultOpenAIClient(gateway);
```
AI Gateway logs every interaction with LLMs, including:
* Complete request and response payloads
* Latency and token usage metrics
* Cost calculations
* Tool calls and function executions
All logs can be filtered by metadata, trace IDs, models, and more, making it easy to debug specific agent runs.
The AI Gateway provides built-in dashboards that help you:
* Track cost and token usage across all agent runs
* Analyze performance metrics like latency and success rates
* Identify bottlenecks in your agent workflows
* Compare different agent configurations and LLMs
You can filter and segment all metrics by custom metadata to analyze specific agent types, user groups, or use cases.
Add custom metadata to your OpenAI agent calls to enable powerful filtering and segmentation:
```typescript theme={"system"}
// Add metadata to your OpenAI Agents
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: {
"x-portkey-provider": "@YOUR_OPENAI_PROVIDER",
// Add custom metadata
"x-portkey-metadata": JSON.stringify({"agent_type": "research_agent"}),
}
});
setDefaultOpenAIClient(gateway);
```
This metadata can be used to filter logs, traces, and metrics on Strata Cloud Manager, allowing you to analyze specific agent runs, users, or environments.
### 2. Reliability - Keep Your Agents Running Smoothly
When running agents in production, things can go wrong - API rate limits, network issues, or provider outages. The AI Gateway's reliability features ensure your agents keep running smoothly even when problems occur.
It's this simple to enable fallback in your OpenAI Agents:
```typescript theme={"system"}
import { OpenAI } from 'openai';
import { setDefaultOpenAIClient } from '@openai/agents';
// Create a config with fallbacks, Prefer creating the Config in Strata Cloud Manager over hard-coding the config JSON
const config = {
"strategy": {
"mode": "fallback"
},
"targets": [
{
"provider": "openai",
"override_params": {"model": "gpt-4o"}
},
{
"provider": "anthropic",
"override_params": {"model": "claude-3-opus-20240229"}
}
]
};
// Configure the AI Gateway client with fallback config
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: { "x-portkey-config": JSON.stringify(config) }
});
setDefaultOpenAIClient(gateway);
```
This configuration will automatically try Claude if the GPT-4o request fails, ensuring your agent can continue operating.
Handles temporary failures automatically. If an LLM call fails, the AI Gateway will retry the same request for the specified number of times - perfect for rate limits or network blips.
Prevent your agents from hanging. Set timeouts to ensure you get responses (or can fail gracefully) within your required timeframes.
Send different requests to different providers. Route complex reasoning to GPT-4, creative tasks to Claude, and quick responses to Gemini based on your needs.
Keep running even if your primary provider fails. Automatically switch to backup providers to maintain availability.
Spread requests across multiple API keys or providers. Great for high-volume agent operations and staying within rate limits.
### 3. Prompting in OpenAI Agents
The AI Gateway's Prompt Engineering Studio helps you create, manage, and optimize the prompts used in your OpenAI Agents. Instead of hardcoding prompts or instructions, use the AI Gateway's prompt rendering API to dynamically fetch and apply your versioned prompts.
Prompt Playground is a place to compare, test and deploy perfect prompts for your AI application. It's where you experiment with different models, test variables, compare outputs, and refine your prompt engineering strategy before deploying to production. It allows you to:
1. Iteratively develop prompts before using them in your agents
2. Test prompts with different variables and models
3. Compare outputs between different prompt versions
4. Collaborate with team members on prompt development
This visual environment makes it easier to craft effective prompts for each step in your OpenAI Agents agent's workflow.
The Prompt Render API retrieves your prompt templates with all parameters configured:
You can:
* Create multiple versions of the same prompt
* Compare performance between versions
* Roll back to previous versions if needed
* Specify which version to use in your code:
```typescript theme={"system"}
// Use a specific prompt version
const promptData = await gatewayClient.prompts.render({
promptId: "YOUR_PROMPT_ID@version_number",
variables: {
user_input: "Tell me about quantum computing"
}
});
```
AI Gateway prompts use Mustache-style templating for easy variable substitution:
```
You are an AI assistant helping with {{task_type}}.
User question: {{user_input}}
Please respond in a {{tone}} tone and include {{required_elements}}.
```
When rendering, simply pass the variables:
```typescript theme={"system"}
const promptData = await gatewayClient.prompts.render({
promptId: "YOUR_PROMPT_ID",
variables: {
task_type: "research",
user_input: "Tell me about quantum computing",
tone: "professional",
required_elements: "recent academic references"
}
});
```
### 4. Guardrails for Safe Agents
Guardrails ensure your OpenAI Agents operate safely and respond appropriately in all situations.
**Why Use Guardrails?**
OpenAI Agents can experience various failure modes:
* Generating harmful or inappropriate content
* Leaking sensitive information like PII
* Hallucinating incorrect information
* Generating outputs in incorrect formats
The AI Gateway's guardrails protect against these issues by validating both inputs and outputs.
**Implementing Guardrails**
```typescript theme={"system"}
import { OpenAI } from 'openai';
import { setDefaultOpenAIClient } from '@openai/agents';
// Create a config with input and output guardrails, Prefer creating the Config in Strata Cloud Manager and passing the config ID in the client
const config = {
"provider":"@openai-xxx",
"input_guardrails": ["guardrails-id-xxx", "guardrails-id-yyy"],
"output_guardrails": ["guardrails-id-xxx"]
};
// Configure OpenAI client with guardrails
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: { "x-portkey-provider": "@YOUR_OPENAI_PROVIDER", "x-portkey-config": JSON.stringify(config) }
});
setDefaultOpenAIClient(gateway);
```
The AI Gateway's guardrails can:
* Detect and redact PII in both inputs and outputs
* Filter harmful or inappropriate content
* Validate response formats against schemas
* Check for hallucinations against ground truth
* Apply custom business logic and rules
Explore the AI Gateway's guardrail features to enhance agent safety
### 5. User Tracking with Metadata
Track individual users through your OpenAI Agents using the AI Gateway's metadata system.
**What is Metadata in the AI Gateway?**
Metadata allows you to associate custom data with each request, enabling filtering, segmentation, and analytics. The special `_user` field is specifically designed for user tracking.
```typescript theme={"system"}
import { OpenAI } from 'openai';
import { setDefaultOpenAIClient } from '@openai/agents';
// Configure client with user tracking
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: {
"x-portkey-provider": "@YOUR_LLM_PROVIDER",
"x-portkey-metadata": JSON.stringify({
"_user": "user_123", // Special _user field for user analytics
"user_name": "John Doe",
"user_tier": "premium",
"user_company": "Acme Corp"
}),
}
});
setDefaultOpenAIClient(gateway);
```
**Filter Analytics by User**
With metadata in place, you can filter analytics by user and analyze performance metrics on a per-user basis:
This enables:
* Per-user cost tracking and budgeting
* Personalized user analytics
* Team or organisation-level metrics
* Environment-specific monitoring (staging vs. production)
Explore how to use custom metadata to enhance your analytics
### 6. Caching for Efficient Agents
Implement caching to make your OpenAI Agents agents more efficient and cost-effective:
```typescript theme={"system"}
const gatewayConfig = {
"cache": {
"mode": "simple"
},
"provider":"@YOUR_LLM_PROVIDER"
};
// Configure OpenAI client with chosen provider
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: { "x-portkey-config": JSON.stringify(gatewayConfig) }
});
setDefaultOpenAIClient(gateway);
```
Simple caching performs exact matches on input prompts, caching identical requests to avoid redundant model executions.
```typescript theme={"system"}
const gatewayConfig = {
"cache": {
"mode": "semantic"
},
"provider":"@YOUR_LLM_PROVIDER"
};
// Configure OpenAI client with chosen provider
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: { "x-portkey-config": JSON.stringify(gatewayConfig) }
});
setDefaultOpenAIClient(gateway);
```
Semantic caching considers the contextual similarity between input requests, caching responses for semantically similar inputs.
### 7. Model Interoperability
With the AI Gateway, you can easily switch between different LLMs in your OpenAI Agents without changing your core agent logic.
```typescript theme={"system"}
// Configure the AI Gateway with different LLM providers
import { OpenAI } from 'openai';
import { setDefaultOpenAIClient, Agent, run } from '@openai/agents';
// Using OpenAI
const openaiConfig = {
"provider": "@openai-prod",
"override_params": {"model": "gpt-4o"}
};
// Using Anthropic
const anthropicConfig = {
"provider": "@anthropic-prod",
"override_params": {"model": "claude-3-5-sonnet-latest"}
};
// Choose which config to use
const activeConfig = openaiConfig; // or anthropicConfig
// Configure OpenAI client with chosen provider
const gateway = new OpenAI({
baseURL: "https://aigw.portkey.ai/v1",
apiKey: process.env.PORTKEY_API_KEY!,
defaultHeaders: { "x-portkey-config": JSON.stringify(activeConfig) }
});
setDefaultOpenAIClient(gateway);
// Create and run agent - no changes needed in agent code
const agent = new Agent({
name: "Assistant",
instructions: "You are a helpful assistant.",
// The model specified here will be used as a reference but the actual model
// is determined by the activeConfig
model: "gpt-4o"
});
const result = await run(agent, "Tell me about quantum computing.");
console.log(result.finalOutput);
```
The AI Gateway provides access to over 200 LLMs through a unified interface, including:
* OpenAI (GPT-4o, GPT-4 Turbo, etc.)
* Anthropic (Claude 3.5 Sonnet, Claude 3 Opus, etc.)
* Mistral AI (Mistral Large, Mistral Medium, etc.)
* Google Vertex AI (Gemini 1.5 Pro, etc.)
* Cohere (Command, Command-R, etc.)
* AWS Bedrock (Claude, Titan, etc.)
* Local/Private Models
See the full list of LLM providers supported by the AI Gateway
## Set Up Enterprise Governance for OpenAI Agents
**Why Enterprise Governance?**
If you are using OpenAI Agents inside your orgnaization, you need to consider several governance aspects:
* **Cost Management**: Controlling and tracking AI spending across teams
* **Access Control**: Managing which teams can use specific models
* **Usage Analytics**: Understanding how AI is being used across the organisation
* **Security & Compliance**: Maintaining enterprise security standards
* **Reliability**: Ensuring consistent service across all users
The AI Gateway adds a comprehensive governance layer to address these enterprise needs. Let's implement these controls step by step.
**Enterprise Implementation Guide**
The AI Gateway allows you to use 3,000+ LLMs with your OpenAI Agents setup, with minimal configuration required. Let's set up the core components in the AI Gateway that you'll need for integration.
Add your LLM provider credentials to Model Catalog. This gives you centralized control with:
* Budget limits per provider
* Rate limiting capabilities
* Secure credential storage
Go to [Model Catalog](https://stratacloudmanager.paloaltonetworks.com/) in Strata Cloud Manager and add your provider. Copy the AI Provider slug — you'll need it for the next step.
Configs in the AI Gateway are JSON objects that define how your requests are routed. They help with implementing features like advanced routing, fallbacks, and retries.
We need to create a default config to route our requests to the AI Provider added in Step 1.
To create your config:
1. Go to [Configs](https://stratacloudmanager.paloaltonetworks.com/) in Strata Cloud Manager
2. Create new config with:
```json theme={"system"}
{
"provider":"@YOUR_PROVIDER_FROM_STEP1",
"override_params": {
"model": "gpt-4o" // Your preferred model name
}
}
```
3. Save and note the Config name for the next step
This basic config connects to your AI Provider. You can add more advanced AI Gateway features later.
Now create AI Gateway API key access point and attach the config you created in Step 2:
1. Go to [API Keys](https://stratacloudmanager.paloaltonetworks.com/) in the AI Gateway and Create new API key
2. Select your config from `Step 2`
3. Generate and save your API key
Save your API key securely - you'll need it for OpenAI Agents integration.
Once you have created your API Key after attaching default config, you can directly pass the API key + base URL in the OpenAI client. Here's how:
```typescript theme={"system"}
import { OpenAI } from 'openai';
const client = new OpenAI({
apiKey: "YOUR_PORTKEY_API_KEY", // Your AI Gateway API key from Step 3
baseURL: "https://aigw.portkey.ai/v1"
});
// your rest of the code remains same
```
### Step 1: Implement Budget Controls & Rate Limits
AI Providers in Model Catalog enable granular control over LLM access at the team/department level. This helps you:
* Set up [budget limits](/docs/aigw/product/policies/budget-limits)
* Prevent unexpected usage spikes using rate limits
* Track departmental spending
#### Setting Up Department-Specific Controls:
1. Navigate to [Model Catalog](https://stratacloudmanager.paloaltonetworks.com/) in Strata Cloud Manager
2. Add an AI Provider for each department with budget limits and rate limits
3. Configure department-specific limits
### Step 2: Define Model Access Rules
As your AI usage scales, controlling which teams can access specific models becomes crucial. AI Gateway Configs provide this control layer with features like:
#### Access Control Features:
* **Model Restrictions**: Limit access to specific models
* **Data Protection**: Implement guardrails for sensitive data
* **Reliability Controls**: Add fallbacks and retry logic
#### Example Configuration:
Here's a basic configuration to route requests to OpenAI, specifically using GPT-4o:
```json theme={"system"}
{
"strategy": {
"mode": "single"
},
"targets": [
{
"provider":"@YOUR_OPENAI_PROVIDER",
"override_params": {
"model": "gpt-4o"
}
}
]
}
```
Create your config on the [Configs page](https://stratacloudmanager.paloaltonetworks.com/) in Strata Cloud Manager. You'll need the config ID for connecting to OpenAI Agents's setup.
Configs can be updated anytime to adjust controls without affecting running applications.
### Step 3: Implement Access Controls
Create User-specific API keys that automatically:
* Track usage per user/team with the help of metadata
* Apply appropriate configs to route requests
* Collect relevant metadata to filter logs
* Enforce access permissions
Create API keys through:
* [Strata Cloud Manager](https://stratacloudmanager.paloaltonetworks.com/)
* [API Key Management API](/docs/api-reference/admin-api/control-plane/api-keys/create-api-key)
Example using TypeScript SDK:
For detailed key management instructions, see our [API Keys documentation](/docs/api-reference/admin-api/control-plane/api-keys/create-api-key).
### Step 4: Deploy & Monitor
After distributing API keys to your team members, your enterprise-ready OpenAI Agents setup is ready to go. Each team member can now use their designated API keys with appropriate access levels and budget controls.
Apply your governance setup using the integration steps from earlier sections
Monitor usage in Strata Cloud Manager:
* Cost tracking by department
* Model usage patterns
* Request volumes
* Error rates
### Enterprise Features Now Available
**OpenAI Agents now has:**
* Departmental budget controls
* Model access governance
* Usage tracking & attribution
* Security guardrails
* Reliability features
## Frequently Asked Questions
The AI Gateway adds production-readiness to OpenAI Agents through comprehensive observability (traces, logs, metrics), reliability features (fallbacks, retries, caching), and access to 3,000+ LLMs through a unified interface. This makes it easier to debug, optimize, and scale your agent applications.
Yes! The AI Gateway integrates seamlessly with existing OpenAI Agents. You only need to replace your client initialization code with the gateway-enabled version. The rest of your agent code remains unchanged.
The AI Gateway supports all OpenAI Agents SDK features, including tool use, memory, planning, and more. It adds observability and reliability without limiting any of the SDK's functionality.
The AI Gateway fully supports streaming responses in OpenAI Agents. You can enable streaming by using the appropriate methods in the OpenAI Agents SDK, and the AI Gateway will properly track and log the streaming interactions.
The AI Gateway allows you to add custom metadata to your agent runs, which you can then use for filtering. Add fields like `agent_name`, `agent_type`, or `session_id` to easily find and analyze specific agent executions.
Yes! The AI Gateway uses your own API keys for the various LLM providers. It securely stores them, allowing you to easily manage and rotate keys without changing your code.
## Resources