ai/docs/03-ai-sdk-core/65-devtools.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: DevTools
description: Debug and inspect AI SDK applications with DevTools
---

# DevTools

<Note type="warning">
  AI SDK DevTools is intended for local development only. Do not use in
  production environments.
</Note>

AI SDK DevTools gives you full visibility over your AI SDK calls with [`generateText`](/docs/reference/ai-sdk-core/generate-text), [`streamText`](/docs/reference/ai-sdk-core/stream-text), and [`ToolLoopAgent`](/docs/reference/ai-sdk-core/tool-loop-agent). It helps you debug and inspect LLM requests, responses, tool calls, and multi-step interactions through a web-based UI.

DevTools is composed of two parts:

1. **Telemetry Integration**: Captures runs and steps from your AI SDK calls via the [telemetry](/docs/ai-sdk-core/telemetry) system
2. **Viewer**: A web UI to inspect the captured data

## Installation

Install the DevTools package:

```bash
pnpm add @ai-sdk/devtools
```

## Requirements

- AI SDK v7 (`ai@latest`)
- Node.js compatible runtime

## Using DevTools

### Register the integration

Register `DevToolsTelemetry` globally so it captures all AI SDK calls:

```ts
import { registerTelemetry } from 'ai';
import { DevToolsTelemetry } from '@ai-sdk/devtools';

registerTelemetry(DevToolsTelemetry());
```

Telemetry is enabled automatically once an integration is registered — no per-call configuration is needed:

```ts
import { generateText } from 'ai';

const result = await generateText({
  model: openai('gpt-4o'),
  prompt: 'What cities are in the United States?',
});
```

You can also pass the integration to individual calls instead of registering it globally:

```ts highlight="7-9"
import { streamText } from 'ai';
import { DevToolsTelemetry } from '@ai-sdk/devtools';

const result = streamText({
  model: openai('gpt-4o'),
  prompt: 'Hello!',
  telemetry: {
    integrations: [DevToolsTelemetry()],
  },
});
```

### Launch the viewer

Start the DevTools viewer:

```bash
npx @ai-sdk/devtools
```

Open [http://localhost:4983](http://localhost:4983) to view your AI SDK interactions.

### Monorepo usage

If you are using a monorepo setup (e.g. Turborepo, Nx), start DevTools from the same workspace where your AI SDK code runs.

For example, if your API is in `apps/api`, run:

```bash
cd apps/api
npx @ai-sdk/devtools
```

## Captured data

DevTools captures the following information from your AI SDK calls:

- **Input parameters and prompts**: View the complete input sent to your LLM
- **Output content and tool calls**: Inspect generated text and tool invocations
- **Token usage and timing**: Monitor resource consumption and performance
- **Raw provider data**: Access complete request and response payloads

### Runs and steps

DevTools organizes captured data into runs and steps:

- **Run**: A complete multi-step AI interaction, grouped by the initial prompt
- **Step**: A single LLM call within a run (e.g., one `generateText` or `streamText` call)

Multi-step interactions, such as those created by tool calling or agent loops, are grouped together as a single run with multiple steps. Nested sub-agent calls are linked to their parent run, making it easy to trace the full execution tree.

## How it works

The `DevToolsTelemetry` integration hooks into the AI SDK [telemetry](/docs/ai-sdk-core/telemetry) lifecycle to capture all `generateText`, `streamText`, `generateObject`, and `streamObject` calls. Captured data is stored locally in a JSON file (`.devtools/generations.json`) and served through a web UI built with Hono and React.

<Note type="warning">
  The integration automatically adds `.devtools` to your `.gitignore` file.
  Verify that `.devtools` is in your `.gitignore` to ensure you don't commit
  sensitive AI interaction data to your repository.
</Note>

## Security considerations

DevTools stores all AI interactions locally in plain text files, including:

- User prompts and messages
- LLM responses
- Tool call arguments and results
- API request and response data

**Only use DevTools in local development environments.** Do not enable DevTools in production or when handling sensitive data.