> ## 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.

# Overview

> The Prisma AIRS AI Gateway helps bring your agents to production

<CardGroup cols={4}>
  <Card title="OpenAI Agents (Python)" href="/docs/aigw/integrations/agents/openai-agents" />

  <Card title="OpenAI Agents (Type Script)" href="/docs/aigw/integrations/agents/openai-agents-ts" />

  <Card title="AWS AgentCore" href="/docs/aigw/integrations/agents/agentcore" />

  <Card title="Pydantic AI" href="/docs/aigw/integrations/agents/pydantic-ai" />

  <Card title="Autogen" href="/docs/aigw/integrations/agents/autogen" />

  <Card title="CrewAI" href="/docs/aigw/integrations/agents/crewai" />

  <Card title="Agno AI" href="/docs/aigw/integrations/agents/agno-ai" />

  <Card title="Mastra Agents" href="/docs/aigw/integrations/agents/mastra-agents" />

  <Card title="Llama Index" href="/docs/aigw/integrations/agents/llama-agents" />

  <Card title="LangChain" href="/docs/aigw/integrations/agents/langchain-agents" />

  <Card title="LangGraph" href="/docs/aigw/integrations/agents/langgraph" />

  <Card title="Langroid" href="/docs/aigw/integrations/agents/langroid" />

  <Card title="OpenAI Swarm" href="/docs/aigw/integrations/agents/openai-swarm" />

  <Card title="Control Flow" href="/docs/aigw/integrations/agents/control-flow" />

  <Card title="AWS AgentCore" href="/docs/aigw/integrations/agents/agentcore" />

  <Card title="Strands Agents" href="/docs/aigw/integrations/agents/strands" />

  <Card title="Bring Your Agent" href="/docs/aigw/integrations/agents/bring-your-own-agents" />
</CardGroup>

## Integrate the AI Gateway with your agents with just 2 lines of code

### Get Started with the AI Gateway x Agent Cookbooks

* [Autogen](https://dub.sh/Autogen-docs)
* [CrewAI](https://git.new/crewAI-docs)
* [Phidata](https://dub.sh/Phidata-docs)
* [Llama Index ](https://git.new/llama-agents)
* [Control Flow](https://dub.sh/Control-Flow-docs)

***

## Key Production Features

By routing your agent's requests through the AI Gateway, you make your agents production-grade with the following features.

### 1. [Interoperability](/docs/aigw/product/ai-gateway/universal-api)

Easily switch between LLM providers. Call various LLMs such as Anthropic, Gemini, Mistral, Azure OpenAI, Google Vertex AI, AWS Bedrock and much more by simply changing the `provider ` and `API key` in the LLM object.

### 2. [Caching](/docs/aigw/product/ai-gateway/cache-simple-and-semantic)

Improve performance and reduce costs on your Agent's LLM calls by storing past responses in the AI Gateway cache. Choose between Simple and Semantic cache modes in your AI Gateway config.

```json theme={"system"}
{
 "cache": {
    "mode": "semantic" // Choose between "simple" or "semantic"
 }
}
```

### 3. [Reliability](/docs/aigw/product/ai-gateway)

Set up **fallbacks** between different LLMs or providers, **load balance** your requests across multiple instances or API keys, set **automatic retries**, and **request timeouts.** Ensure your agents' resilience with advanced reliability features.

```json theme={"system"}
{
  "retry": {
    "attempts": 5
  },
  "strategy": {
    "mode": "loadbalance" // Choose between "loadbalance" or "fallback"
  },
  "targets": [
    {
      "provider": "openai",
      "api_key": "OpenAI_API_Key"
    },
    {
      "provider": "anthropic",
      "api_key": "Anthropic_API_Key"
    }
  ]
}
```

### 4. [Observability](/docs/aigw/product/observability)

The AI Gateway automatically logs key details about your agent runs, including cost, tokens used, response time, etc. For agent-specific observability, add Trace IDs to the request headers for each agent. This enables filtering analytics by Trace IDs, ensuring deeper monitoring and analysis.

### 5. [Logs](/docs/aigw/product/observability/logs)

Access a dedicated section to view records of action executions, including parameters, outcomes, and errors. Filter logs of your agent run based on multiple parameters such as trace ID, model, tokens used, metadata, etc.

### 6. Prompt Management

Use the AI Gateway as a centralized hub to store, version, and experiment with your agent's prompts across multiple LLMs. Easily modify your prompts and run A/B tests without worrying about the breaking prod.

### 7. [Continuous Improvement](/docs/aigw/product/observability/feedback)

Improve your Agent runs by capturing qualitative & quantitative user feedback on your requests, and then using that feedback to make your prompts AND LLMs themselves better.

### 8. [Security & Compliance](/docs/aigw/product/enterprise-offering/security)

Set budget limits on provider API keys and implement fine-grained user roles and permissions for both the app and the AI Gateway APIs.


## Related topics

- [Overview](/docs/aigw/integrations/overview.md)