> ## 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.

# Mastra Agents

> Use Prisma AIRS AI Gateway with Mastra to take your AI Agents to production

## Introduction

Mastra is a TypeScript framework for building AI agents with tools, workflows, memory, and evaluation scoring. The AI Gateway enhances Mastra agents with observability, reliability, and production-readiness features.

The AI Gateway turns your experimental Mastra 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

<Card title="Mastra Official Documentation" icon="arrow-up-right-from-square" href="https://mastra.ai/docs">
  Learn more about Mastra's core concepts and features
</Card>

### Installation & Setup

<Steps>
  <Step title="Install the required packages">
    ```bash theme={"system"}
    npm install @mastra/core
    npm install --save-dev mastra
    ```
  </Step>

  <Step title="Generate API Key">
    Create an AI Gateway API key from the [Strata Cloud Manager](https://stratacloudmanager.paloaltonetworks.com/). You can attach optional budget/rate limits and configurations.
  </Step>

  <Step title="Set Up Provider Integration">
    In the AI Gateway, set up your LLM provider integration:

    1. Go to [Integrations](https://stratacloudmanager.paloaltonetworks.com/) in the AI Gateway
    2. Connect your LLM provider (OpenAI, Anthropic, etc.)
    3. Note your provider slug (e.g., `openai-dev`, `anthropic-prod`)

    You'll use this slug in your Mastra model configuration.
  </Step>

  <Step title="Configure Mastra Agent with the AI Gateway">
    Configure your Mastra agent's model to use the AI Gateway as the gateway:

    ```typescript theme={"system"}
    import { Agent } from '@mastra/core/agent';

    export const agent = new Agent({
      name: 'Assistant',
      instructions: 'You are a helpful assistant.',
      model: {
        id: 'openai/@YOUR_PROVIDER_SLUG@gpt-4o',  // Format: openai/@provider-slug@model-name
        url: 'https://aigw.portkey.ai/v1',
        apiKey: 'YOUR_PORTKEY_API_KEY',
        headers: {
          // Optional: Add AI Gateway configuration
          'x-portkey-trace-id': 'agent-session-123',
          'x-portkey-metadata': JSON.stringify({
            agent: 'assistant',
            env: 'production'
          })
        }
      }
    });
    ```

    <Note>
      **Model ID Format**: Use `openai/@provider-slug@model-name` because Mastra uses OpenAI-compatible interfaces under the hood. The `@provider-slug` should match the slug from your AI Gateway integration.
    </Note>
  </Step>
</Steps>

## Production Features

### 1. Enhanced Observability

The AI Gateway provides comprehensive observability for your Mastra agents, helping you understand exactly what's happening during each execution.

<Tabs>
  <Tab title="Traces">
    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 Mastra agents
    export const agent = new Agent({
      name: 'Research Assistant',
      instructions: 'You are a helpful research assistant.',
      model: {
        id: 'openai/@YOUR_PROVIDER_SLUG@gpt-4o',
        url: 'https://aigw.portkey.ai/v1',
        apiKey: process.env.PORTKEY_API_KEY,
        headers: {
          'x-portkey-trace-id': 'unique_execution_trace_id', // Add unique trace ID
          'x-portkey-metadata': JSON.stringify({
            agent_type: 'research_agent'
          })
        }
      }
    });
    ```
  </Tab>

  <Tab title="Logs">
    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.
  </Tab>

  <Tab title="Metrics & Dashboards">
    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.
  </Tab>

  <Tab title="Metadata Filtering">
    Add custom metadata to your Mastra agent calls to enable powerful filtering and segmentation:

    ```typescript theme={"system"}
    export const agent = new Agent({
      name: 'Assistant',
      instructions: 'You are a helpful assistant.',
      model: {
        id: 'openai/@YOUR_PROVIDER_SLUG@gpt-4o',
        url: 'https://aigw.portkey.ai/v1',
        apiKey: process.env.PORTKEY_API_KEY,
        headers: {
          'x-portkey-metadata': JSON.stringify({
            agent_type: 'research_agent',
            environment: 'production',
            _user: 'user_123',  // Special _user field for user analytics
            team: 'engineering'
          })
        }
      }
    });
    ```

    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.
  </Tab>
</Tabs>

### 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 Mastra agents:

```typescript theme={"system"}
import { Agent } from '@mastra/core/agent';

// Create a config with fallbacks
// Prefer creating the Config in Strata Cloud Manager over hard-coding the config JSON
const gatewayConfig = {
  strategy: {
    mode: 'fallback'
  },
  targets: [
    {
      provider: '@YOUR_OPENAI_PROVIDER',
      override_params: { model: 'gpt-4o' }
    },
    {
      provider: '@YOUR_ANTHROPIC_PROVIDER',
      override_params: { model: 'claude-3-opus-20240229' }
    }
  ]
};

export const agent = new Agent({
  name: 'Resilient Agent',
  instructions: 'You are a helpful assistant.',
  model: {
    id: 'openai/@YOUR_OPENAI_PROVIDER@gpt-4o',
    url: 'https://aigw.portkey.ai/v1',
    apiKey: process.env.PORTKEY_API_KEY,
    headers: {
      'x-portkey-config': JSON.stringify(gatewayConfig)
    }
  }
});
```

This configuration will automatically try Claude if the GPT-4o request fails, ensuring your agent can continue operating.

<CardGroup cols="2">
  <Card title="Automatic Retries" icon="rotate" href="../../product/ai-gateway/automatic-retries">
    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.
  </Card>

  <Card title="Request Timeouts" icon="clock" href="../../product/ai-gateway/request-timeouts">
    Prevent your agents from hanging. Set timeouts to ensure you get responses (or can fail gracefully) within your required timeframes.
  </Card>

  <Card title="Conditional Routing" icon="route" href="../../product/ai-gateway/conditional-routing">
    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.
  </Card>

  <Card title="Fallbacks" icon="shield" href="../../product/ai-gateway/fallbacks">
    Keep running even if your primary provider fails. Automatically switch to backup providers to maintain availability.
  </Card>

  <Card title="Load Balancing" icon="scale-balanced" href="../../product/ai-gateway/load-balancing">
    Spread requests across multiple API keys or providers. Great for high-volume agent operations and staying within rate limits.
  </Card>
</CardGroup>

### 3. Prompting in Mastra Agents

The AI Gateway's Prompt Engineering Studio helps you create, manage, and optimize the prompts used in your Mastra agents. Instead of hardcoding prompts or instructions, use the AI Gateway's prompt rendering API to dynamically fetch and apply your versioned prompts.

<Tabs>
  <Tab title="Prompt Playground">
    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 Mastra agent's workflow.
  </Tab>

  <Tab title="Using Prompt Templates">
    The Prompt Render API retrieves your prompt templates with all parameters configured:
  </Tab>

  <Tab title="Prompt Versioning">
    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 request
  </Tab>

  <Tab title="Mustache Templating for variables">
    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:
  </Tab>
</Tabs>

### 4. Guardrails for Safe Agents

Guardrails ensure your Mastra agents operate safely and respond appropriately in all situations.

**Why Use Guardrails?**

Mastra 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 { Agent } from '@mastra/core/agent';

// Create a config with input and output guardrails
// Prefer creating the Config in Strata Cloud Manager and passing the config ID in the headers
const guardrailConfig = {
  provider: '@YOUR_PROVIDER',
  input_guardrails: ['guardrails-id-xxx', 'guardrails-id-yyy'],
  output_guardrails: ['guardrails-id-xxx']
};

export const agent = new Agent({
  name: 'Safe Agent',
  instructions: 'You are a helpful assistant that provides safe responses.',
  model: {
    id: 'openai/@YOUR_PROVIDER_SLUG@gpt-4o',
    url: 'https://aigw.portkey.ai/v1',
    apiKey: process.env.PORTKEY_API_KEY,
    headers: {
      'x-portkey-config': JSON.stringify(guardrailConfig)
    }
  }
});
```

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

<Card title="Learn More About Guardrails" icon="shield-check" href="/docs/aigw/product/guardrails">
  Explore the AI Gateway's guardrail features to enhance agent safety
</Card>

### 5. User Tracking with Metadata

Track individual users through your Mastra 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 { Agent } from '@mastra/core/agent';

export const agent = new Agent({
  name: 'Personalized Agent',
  instructions: 'You are a personalized assistant.',
  model: {
    id: 'openai/@YOUR_PROVIDER_SLUG@gpt-4o',
    url: 'https://aigw.portkey.ai/v1',
    apiKey: process.env.PORTKEY_API_KEY,
    headers: {
      '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'
      })
    }
  }
});
```

**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)

<Card title="Learn More About Metadata" icon="tags" href="/docs/aigw/product/observability/metadata">
  Explore how to use custom metadata to enhance your analytics
</Card>

### 6. Caching for Efficient Agents

Implement caching to make your Mastra agents more efficient and cost-effective:

<Tabs>
  <Tab title="Simple Caching">
    ```typescript theme={"system"}
    import { Agent } from '@mastra/core/agent';

    const cacheConfig = {
      provider: '@YOUR_PROVIDER',
      cache: {
        mode: 'simple'
      }
    };

    export const agent = new Agent({
      name: 'Cached Agent',
      instructions: 'You are a helpful assistant.',
      model: {
        id: 'openai/@YOUR_PROVIDER_SLUG@gpt-4o',
        url: 'https://aigw.portkey.ai/v1',
        apiKey: process.env.PORTKEY_API_KEY,
        headers: {
          'x-portkey-config': JSON.stringify(cacheConfig)
        }
      }
    });
    ```

    Simple caching performs exact matches on input prompts, caching identical requests to avoid redundant model executions.
  </Tab>

  <Tab title="Semantic Caching">
    ```typescript theme={"system"}
    import { Agent } from '@mastra/core/agent';

    const semanticCacheConfig = {
      provider: '@YOUR_PROVIDER',
      cache: {
        mode: 'semantic'
      }
    };

    export const agent = new Agent({
      name: 'Semantically Cached Agent',
      instructions: 'You are a helpful assistant.',
      model: {
        id: 'openai/@YOUR_PROVIDER_SLUG@gpt-4o',
        url: 'https://aigw.portkey.ai/v1',
        apiKey: process.env.PORTKEY_API_KEY,
        headers: {
          'x-portkey-config': JSON.stringify(semanticCacheConfig)
        }
      }
    });
    ```

    Semantic caching considers the contextual similarity between input requests, caching responses for semantically similar inputs.
  </Tab>
</Tabs>

### 7. Model Interoperability

With the AI Gateway, you can easily switch between different LLMs in your Mastra agents without changing your core agent logic.

```typescript theme={"system"}
import { Agent } from '@mastra/core/agent';

// Using OpenAI
const openaiAgent = new Agent({
  name: 'OpenAI Agent',
  instructions: 'You are a helpful assistant.',
  model: {
    id: 'openai/@YOUR_OPENAI_PROVIDER@gpt-4o',
    url: 'https://aigw.portkey.ai/v1',
    apiKey: process.env.PORTKEY_API_KEY
  }
});

// Using Anthropic
const anthropicAgent = new Agent({
  name: 'Anthropic Agent',
  instructions: 'You are a helpful assistant.',
  model: {
    id: 'openai/@YOUR_ANTHROPIC_PROVIDER@claude-3-opus-20240229',
    url: 'https://aigw.portkey.ai/v1',
    apiKey: process.env.PORTKEY_API_KEY
  }
});

// Using Google Gemini
const geminiAgent = new Agent({
  name: 'Gemini Agent',
  instructions: 'You are a helpful assistant.',
  model: {
    id: 'openai/@YOUR_GOOGLE_PROVIDER@gemini-2.0-flash-exp',
    url: 'https://aigw.portkey.ai/v1',
    apiKey: process.env.PORTKEY_API_KEY
  }
});
```

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

<Card title="Supported Providers" icon="server" href="/docs/aigw/integrations/llms">
  See the full list of LLM providers supported by the AI Gateway
</Card>

## Set Up Enterprise Governance for Mastra Agents

**Why Enterprise Governance?**

If you are using Mastra agents inside your organisation, 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 Mastra agents setup, with minimal configuration required. Let's set up the core components in the AI Gateway that you'll need for integration.

<Steps>
  <Step title="Create Integration">
    To create a new LLM integration:

    Go to [Integrations](https://stratacloudmanager.paloaltonetworks.com/) in Strata Cloud Manager. Set budget / rate limits, model access if required and save the integration.

    This creates a "AI Gateway Provider" that you can then use in any of your AI Gateway requests without having to send auth details for that LLM provider again.
  </Step>

  <Step title="Create Config">
    Configs in the AI Gateway define how your requests are routed, with features like advanced routing, fallbacks, and retries.

    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 ID for the next step
  </Step>

  <Step title="Configure AI Gateway API Key">
    Now create an AI Gateway API key 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
  </Step>

  <Step title="Connect to Mastra">
    After setting up your AI Gateway API key with the attached config, connect it to your Mastra agents:

    ```typescript theme={"system"}
    import { Agent } from '@mastra/core/agent';

    export const agent = new Agent({
      name: 'Enterprise Agent',
      instructions: 'You are a helpful assistant.',
      model: {
        id: 'openai/@YOUR_PROVIDER_SLUG@gpt-4o',
        url: 'https://aigw.portkey.ai/v1',
        apiKey: 'YOUR_PORTKEY_API_KEY'  // The API key with attached config from step 3
      }
    });
    ```
  </Step>
</Steps>

<AccordionGroup>
  <Accordion title="Step 1: Implement Budget Controls & Rate Limits">
    ### Step 1: Implement Budget Controls & Rate Limits

    Integrations 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 [Integrations](https://stratacloudmanager.paloaltonetworks.com/) in Strata Cloud Manager and create a new Integration
    2. Provision this Integration for each department with their budget limits and rate limits
    3. Configure model access if required
  </Accordion>

  <Accordion title="Step 2: Define Model Access Rules">
    ### 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.

    <Note>
      Configs can be updated anytime to adjust controls without affecting running applications.
    </Note>
  </Accordion>

  <Accordion title="Step 3: Implement Access Controls">
    ### 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 Node.js SDK:

    For detailed key management instructions, see our [API Keys documentation](/docs/api-reference/admin-api/control-plane/api-keys/create-api-key).
  </Accordion>

  <Accordion title="Step 4: Deploy & Monitor">
    ### Step 4: Deploy & Monitor

    After distributing API keys to your team members, your enterprise-ready Mastra 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
  </Accordion>
</AccordionGroup>

<Check>
  ### Enterprise Features Now Available

  **Mastra agents now has:**

  * Departmental budget controls
  * Model access governance
  * Usage tracking & attribution
  * Security guardrails
  * Reliability features
</Check>

## Frequently Asked Questions

<AccordionGroup>
  <Accordion title="How does the AI Gateway enhance Mastra agents?">
    The AI Gateway adds production-readiness to Mastra 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.
  </Accordion>

  <Accordion title="Can I use the AI Gateway with existing Mastra agents?">
    Yes! The AI Gateway integrates seamlessly with existing Mastra agents. You only need to update your agent's model configuration to point to the AI Gateway. The rest of your agent code remains unchanged.
  </Accordion>

  <Accordion title="Does the AI Gateway work with all Mastra features?">
    The AI Gateway supports all Mastra features, including tools, workflows, memory, and scoring. It adds observability and reliability without limiting any of the framework's functionality.
  </Accordion>

  <Accordion title="Why does the model ID use 'openai/' prefix?">
    Mastra uses OpenAI-compatible interfaces under the hood, so the model ID format is `openai/@provider-slug@model-name`. This allows Mastra to work with any LLM provider through the AI Gateway, not just OpenAI. The `@provider-slug` corresponds to your AI Gateway integration slug.
  </Accordion>

  <Accordion title="How do I filter logs and traces for specific agent runs?">
    The AI Gateway allows you to add custom metadata and trace IDs to your agent runs through the model headers. Add fields like `agent_name`, `agent_type`, or `session_id` to easily find and analyze specific agent executions.
  </Accordion>

  <Accordion title="Can I use different LLM providers for different agents?">
    Yes! Simply change the provider slug in the model ID. For example, use `openai/@openai-provider@gpt-4o` for one agent and `openai/@anthropic-provider@claude-3-opus-20240229` for another. All agents route through the AI Gateway.
  </Accordion>
</AccordionGroup>

## Resources

<CardGroup cols="3">
  <Card title="Mastra Docs" icon="book" href="https://mastra.ai/docs">
    <p>Official Mastra documentation</p>
  </Card>

  <Card title="Mastra Examples" icon="code" href="https://github.com/mastra-ai/mastra/tree/main/examples">
    <p>Example implementations for various use cases</p>
  </Card>
</CardGroup>


## Related topics

- [Overview](/docs/aigw/integrations/agents.md)
- [Agent Gateway](/docs/aigw/product/agent-gateway.md)
- [Agent Servers](/docs/aigw/product/agent-gateway/servers.md)
- [Agent Catalog](/docs/aigw/product/catalogs/agents.md)
- [Agent Registry](/docs/aigw/product/agent-gateway/registry.md)