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

# Introduction

> LLM observability for production AI applications

## What is Fallom?

Fallom is an **LLM observability platform** that gives you complete visibility into your AI applications. Understand what's happening in production, debug issues fast, and optimize costs.

<CardGroup cols={2}>
  <Card title="🔍 Observability" icon="chart-line">
    Every LLM call traced with tokens, latency, costs, prompts, and completions
  </Card>

  <Card title="📊 Session Analytics" icon="users">
    Group calls by user or conversation. See the full picture.
  </Card>

  <Card title="🧪 A/B Testing" icon="flask">
    Test models and prompts in production with traffic splitting
  </Card>

  <Card title="📋 Evals" icon="clipboard-check">
    Run evaluations on your LLM outputs at scale
  </Card>
</CardGroup>

<Card title="Get started in 2 minutes" icon="rocket" href="/quickstart" horizontal>
  Add 3 lines of code and start seeing your LLM calls.
</Card>

## How It Works

```typescript theme={null}
import fallom from "@fallom/trace";

await fallom.init({ apiKey: process.env.FALLOM_API_KEY });
const session = fallom.session({ configKey: "my-app", sessionId: "user-123" });

// Wrap your LLM client - that's it
const openai = session.wrapOpenAI(new OpenAI());
```

Every call through `openai` is now automatically traced to your [dashboard](https://app.fallom.com).

## Supported Providers

Works with any OpenAI-compatible API:

* **OpenAI** - GPT-4o, GPT-4, GPT-3.5
* **Anthropic** - Claude 3.5, Claude 3
* **Google** - Gemini Pro, Gemini Flash
* **OpenRouter** - Access 100+ models
* **Vercel AI SDK** - Full framework support

<CardGroup cols={2}>
  <Card title="Python" icon="python">
    `pip install fallom`
  </Card>

  <Card title="TypeScript" icon="js">
    `npm install @fallom/trace`
  </Card>
</CardGroup>