ai/docs/07-reference/06-ai-sdk-tui/01-run-agent-tui.mdx

AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.

---
title: runAgentTUI
description: API Reference for the runAgentTUI function.
---

# `runAgentTUI()`

Runs a `ToolLoopAgent` in an interactive terminal UI. The terminal UI reads user
prompts, streams assistant responses, renders markdown, displays tool and
reasoning sections, and handles manual tool approvals.

`runAgentTUI` runs until the user exits with `Esc` or `Ctrl+C`.

```ts
import { openai } from '@ai-sdk/openai';
import { runAgentTUI } from '@ai-sdk/tui';
import { ToolLoopAgent } from 'ai';

const agent = new ToolLoopAgent({
  model: openai('gpt-5'),
  instructions: 'You are a helpful terminal assistant.',
});

await runAgentTUI({
  title: 'Assistant',
  agent,
});
```

## Import

<Snippet text={`import { runAgentTUI } from "@ai-sdk/tui"`} prompt={false} />

## API Signature

### Parameters

<PropertiesTable
  content={[
    {
      name: 'options',
      type: 'RunAgentTUIOptions',
      isRequired: true,
      description: 'Options for starting the terminal UI.',
      properties: [
        {
          type: 'RunAgentTUIOptions',
          parameters: [
            {
              name: 'agent',
              type: 'AgentTUIAgent',
              isRequired: true,
              description:
                'The agent to run. The agent must not require per-call options and must not use structured output.',
            },
            {
              name: 'title',
              type: 'string',
              isOptional: true,
              description:
                'The title shown in the terminal UI. If omitted, no title is shown.',
            },
            {
              name: 'tools',
              type: "'full' | 'collapsed' | 'auto-collapsed' | 'hidden'",
              isOptional: true,
              description:
                'Controls how tool call sections are displayed. Defaults to `auto-collapsed`.',
            },
            {
              name: 'reasoning',
              type: "'full' | 'collapsed' | 'auto-collapsed' | 'hidden'",
              isOptional: true,
              description:
                'Controls how reasoning sections are displayed. Defaults to `auto-collapsed`.',
            },
            {
              name: 'responseStatistics',
              type: "'outputTokenCount' | 'outputTokensPerSecond'",
              isOptional: true,
              description:
                'Controls which response statistic is shown in response headers. Defaults to `outputTokensPerSecond`.',
            },
            {
              name: 'contextSize',
              type: 'number',
              isOptional: true,
              description:
                'The model context window size in tokens. When provided, the terminal UI shows total token usage as a percentage of this context window.',
            },
            {
              name: 'sandbox',
              type: 'Experimental_SandboxSession',
              isOptional: true,
              description:
                'Sandbox session that is passed through to the agent as `experimental_sandbox` on every call.',
            },
          ],
        },
      ],
    },
  ]}
/>

### Returns

<PropertiesTable
  content={[
    {
      name: 'returns',
      type: 'Promise<void>',
      description: 'A promise that resolves when the terminal UI exits.',
    },
  ]}
/>

## Types

### `AgentTUIAgent`

An agent that is compatible with the terminal UI:

```ts
type AgentTUIAgent = Agent<undefined, any, any, never>;
```

This means the agent has no per-call options and no structured output.

### `TerminalPartDisplayMode`

Controls how terminal sections are displayed:

```ts
type TerminalPartDisplayMode =
  | 'full'
  | 'collapsed'
  | 'auto-collapsed'
  | 'hidden';
```

- `"full"`: Show the section header and full content.
- `"collapsed"`: Show only the section header.
- `"auto-collapsed"`: Show the latest section expanded until another visible
  section appears, then collapse it.
- `"hidden"`: Omit the section entirely.

### `ResponseStatisticsMode`

Controls which response statistic is shown:

```ts
type ResponseStatisticsMode = 'outputTokenCount' | 'outputTokensPerSecond';
```

- `"outputTokenCount"`: Show the number of output tokens in the response.
- `"outputTokensPerSecond"`: Show output token throughput for the response.

## Example with Tool Display Options

```ts
await runAgentTUI({
  title: 'Assistant',
  agent,
  tools: 'auto-collapsed',
  reasoning: 'collapsed',
  responseStatistics: 'outputTokenCount',
  contextSize: 200_000,
});
```

## Example with Sandbox

```ts
import { createJustBashSandbox } from '@ai-sdk/sandbox-just-bash';

const sandboxSession = await createJustBashSandbox({
  cwd: '/home/user',
}).createSession();

await runAgentTUI({
  title: 'Sandbox Assistant',
  agent,
  sandbox: sandboxSession.restricted(),
});
```

The sandbox is forwarded to every `agent.stream()` call as
`experimental_sandbox`, making it available to tool description functions and
tool `execute` functions. Include the sandbox description in the agent
instructions when the model should know sandbox-specific details such as the
working directory or exposed ports.

## Compatibility

Use `runAgentTUI` for agents that can run directly from free-form user input.
Use `agent.generate()` or `agent.stream()` directly when you need fixed prompts,
per-call options, structured output, custom result inspection, or custom stream
processing.

## Related

- [Terminal UI guide](/docs/agents/terminal-ui)
- [Building Agents](/docs/agents/building-agents)
- [ToolLoopAgent guide](/docs/agents/overview#tooloopagent-class)