> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentmuxer.com/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Agents

> Build a research agent with AgentMuxer and OpenAI Agents.

In this guide, you'll build an agent that researches the latest TypeScript release and reports what it found, its sources, and the tool cost.

<Accordion title="Add to an existing agent">
  Import the helper and add it to your agent's `tools`:

  ```typescript theme={null}
  import { agentmuxer } from "@agentmuxer/sdk/openai";
  import { Agent } from "@openai/agents";

  const agent = new Agent({
    name: "Research assistant",
    tools: [agentmuxer()],
  });
  ```
</Accordion>

## Before you start

* Node.js 22.18 or later with ESM; see [compatibility](/reference/compatibility).
* An [AgentMuxer application key](/sdk/applications) and credits for paid calls.
* An OpenAI API key for the model.

<Note>
  This example asks the agent to spend up to \$0.10 on one tool call. Model charges are separate. Set an [application spending limit](/sdk/applications) if you need a hard cap; the prompt alone doesn't enforce one.

  This example cannot collect payment confirmation. [Configure your account for unattended purchases](/guides/billing#unattended-applications) before running it. This setting also affects your personal agents.
</Note>

<Steps>
  <Step title="Install">
    In a new directory, create an ESM project and install the integration:

    ```bash theme={null}
    mkdir my-agent
    cd my-agent
    npm init -y
    npm pkg set type=module
    npm install @agentmuxer/sdk @openai/agents
    ```
  </Step>

  <Step title="Set your keys">
    Set both keys in your terminal:

    ```bash theme={null}
    export AGENTMUXER_API_KEY='your-application-key'
    export OPENAI_API_KEY='your-model-provider-key'
    ```

    No browser sign-in is needed. Keep both keys on your server and out of source control.
  </Step>

  <Step title="Create your agent">
    Save this as `agent.ts`:

    ```typescript agent.ts highlight={10} theme={null}
    import { agentmuxer } from "@agentmuxer/sdk/openai";
    import { Agent, run } from "@openai/agents";

    const prompt = `Use AgentMuxer to research the latest TypeScript release.
    Summarize three changes with sources and report the tool cost.
    Spend at most $0.10 on one tool call. Stop if it costs more.`;

    const agent = new Agent({
      name: "Research assistant",
      tools: [agentmuxer()],
    });
    const result = await run(agent, prompt);
    console.log(result.finalOutput);
    ```
  </Step>

  <Step title="Run">
    ```bash theme={null}
    node agent.ts
    ```

    The example asks the agent to print:

    * Three TypeScript release changes.
    * Sources for the summary.
    * The actual tool cost, or the reason it could not complete the purchase.

    To try another task, edit `prompt`. Include the spending you allow.
  </Step>
</Steps>

## Customize permissions

`agentmuxer()` exposes all AgentMuxer tools, including purchases. OpenAI tool approval defaults to `requireApproval: "never"`; AgentMuxer's spending and payment-confirmation controls still apply.

Pass `allowedTools` to filter exposed tools. For OpenAI approval prompts, pass `requireApproval: "always"` and implement [approval interruptions and resumption](https://openai.github.io/openai-agents-js/guides/human-in-the-loop/).

OpenAI receives the application key and connects to AgentMuxer on your behalf. See the [SDK reference](/reference/sdk) for all options.

<CardGroup cols={2}>
  <Card title="Applications and keys" icon="key" href="/sdk/applications">
    Manage credentials and spending limits.
  </Card>

  <Card title="Run in production" icon="server" href="/sdk/production">
    Handle deployment, failures, and tracing.
  </Card>
</CardGroup>