# Moda

> Moda is a product analytics and observability platform for LLM-native software. It provides automatic conversation threading, pattern discovery, and analytics for chatbots, copilots, and agents.

## Getting Started

- [Overview](https://docs.moda.dev): What Moda is and how it works
- [Quick Start](https://docs.moda.dev/quickstart): Get started with Moda in 5 minutes
- [Prompt Management](https://docs.moda.dev/prompt-management/overview): Code-first prompt sync, versioning, labels, runtime attribution, and dashboard visibility
- [Prompt Quickstart](https://docs.moda.dev/prompt-management/quickstart): `moda init`, `.moda/prompts.yml`, `moda prompts status`, `moda prompts sync`, and SDK rendering

## Ingestion

- [Python SDK](https://docs.moda.dev/ingestion/moda-sdk): Automatic LLM analytics for Python (pip install moda-ai)
- [Node.js SDK](https://docs.moda.dev/ingestion/moda-sdk-node): Automatic LLM analytics for TypeScript/Node.js (npm install moda-ai)
- [Direct API](https://docs.moda.dev/ingestion/direct-api): Send data directly via HTTP API

## Providers

- [OpenAI](https://docs.moda.dev/ingestion/providers/openai): OpenAI integration
- [Anthropic](https://docs.moda.dev/ingestion/providers/anthropic): Anthropic Claude integration
- [OpenRouter](https://docs.moda.dev/ingestion/providers/openrouter): OpenRouter multi-provider integration
- [Azure OpenAI](https://docs.moda.dev/ingestion/providers/azure-openai): Azure OpenAI integration
- [AWS Bedrock](https://docs.moda.dev/ingestion/providers/bedrock): AWS Bedrock integration
- [OpenClaw](https://docs.moda.dev/ingestion/providers/openclaw): OpenClaw OTLP diagnostics integration

## Frameworks

- [Vercel AI SDK](https://docs.moda.dev/ingestion/vercel-ai-sdk): Integration with Vercel AI SDK
- [Vapi](https://docs.moda.dev/ingestion/providers/vapi): Vapi voice AI integration
- [Claude Code Skill](https://docs.moda.dev/ingestion/claude-code-skill): Let AI integrate Moda automatically

## Data API

- [Data API Overview](/data-api/overview): Programmatic access to conversation analytics
- [CLI](/data-api/cli): Terminal analytics and prompt sync commands (`moda prompts status`, `sync`, `promote`)
- [MCP Server](/data-api/mcp): Connect AI assistants to Moda analytics via MCP
- [Use Cases](/data-api/use-cases): Example workflows for monitoring, debugging, and analysis

## Quick Install

Python:
pip install moda-ai

TypeScript/Node.js:
npm install moda-ai

## Quick Start Code

Python:
```python
import moda
from openai import OpenAI

moda.init("YOUR_MODA_API_KEY")
moda.conversation_id = "session_123"

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
moda.flush()
```

TypeScript:
```typescript
import { Moda } from 'moda-ai';
import OpenAI from 'openai';

await Moda.init('YOUR_MODA_API_KEY');
Moda.conversationId = 'session_123';

const client = new OpenAI();
const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
});
await Moda.flush();
```

## Prompt Management Code

TypeScript:
```typescript
const rendered = Moda.prompt('support.triage').render({
  ticket: { text: userMessage },
});

await client.chat.completions.create({
  model: 'gpt-4o',
  messages: rendered.messages,
});
```

Python:
```python
rendered = moda.prompt("support.triage").render({
    "ticket": {"text": user_message},
})

client.chat.completions.create(
    model="gpt-4o",
    messages=rendered["messages"],
)
```

Prompt workflow:
```bash
moda init
moda prompts status
moda prompts sync
moda prompts promote support.triage --label=prod --version=pver_abc123
```