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

# Overview

> Connect AI agents to LP Agent docs and APIs

## AI Integration for LP Agent

LP Agent is AI-friendly by design: clear docs, OpenAPI-powered API reference, and simple REST endpoints with API key authentication.

Use this page to choose the right integration path for your AI agent.

## Pick the Right Tool

The right setup depends on where your agent runs and what it needs to do.

| Goal                                 | Local coding agents (OpenCode, Claude Code, Cursor, Codex)                                                       | Hosted agents (ChatGPT, Claude web, other hosted runtimes)                  |
| ------------------------------------ | ---------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------- |
| **Read docs and learn capabilities** | Use `https://docs.lpagent.io/llms.txt` first, then this docs site + `docs.json` navigation + API reference pages | Use `https://docs.lpagent.io/llms.txt` and this docs site + API reference   |
| **Generate API integrations**        | Use `api-reference/openapi.json` and `/api-reference/introduction`                                               | Use `/api-reference/introduction` and endpoint pages generated from OpenAPI |
| **Execute LP operations**            | Call LP Agent REST APIs with your `x-api-key`                                                                    | Call LP Agent REST APIs from your server/backend with your `x-api-key`      |

<Note>
  Local coding agents can also inspect repository files directly (`docs.json`, `.mdx`, and `api-reference/openapi.json`) to build accurate integrations faster.
</Note>

## Read the Docs Effectively

For agents that need to understand LP Agent before writing code or taking actions.

<Note>
  Start with [`https://docs.lpagent.io/llms.txt`](https://docs.lpagent.io/llms.txt). It is the fastest machine-readable entry point for agents that want a compact index of the docs before following deeper links.
</Note>

<CardGroup cols={2}>
  <Card title="Getting Started" icon="rocket" href="/quickstart">
    Product overview, onboarding flow, and core concepts.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Authentication and full endpoint reference generated from OpenAPI.
  </Card>
</CardGroup>

## Execute Operations via API

For AI systems that need to perform real actions (discover pools, create liquidity transactions, manage positions).

<Steps>
  <Step title="1) Get an API key">
    Create an API key from the [LP Agent Portal](https://portal.lpagent.io/).
  </Step>

  <Step title="2) Authenticate requests">
    Send your API key in the `x-api-key` header for every API request.
  </Step>

  <Step title="3) Follow endpoint workflows">
    Use the API tutorials for end-to-end flows, then adapt to your agent runtime.
  </Step>
</Steps>

<CardGroup cols={2}>
  <Card title="Zap-In & Zap-Out Tutorial" icon="book" href="/tutorials/add-liquidity-api">
    End-to-end API flow for adding and removing liquidity.
  </Card>

  <Card title="Auto Rebalance Tutorial" icon="arrows-rotate" href="/tutorials/auto-rebalance-bot">
    Build an automated bot workflow on top of LP Agent APIs.
  </Card>
</CardGroup>

## Minimal API Request Pattern

```bash theme={null}
curl -X GET "https://api.lpagent.io/open-api/v1/pools/discover?chain=SOL&pageSize=5" \
  -H "x-api-key: YOUR_API_KEY"
```

```typescript theme={null}
const res = await fetch("https://api.lpagent.io/open-api/v1/pools/discover?chain=SOL&pageSize=5", {
  headers: {
    "x-api-key": process.env.LPAGENT_API_KEY!,
  },
});

if (!res.ok) {
  throw new Error(`Request failed: ${res.status}`);
}

const data = await res.json();
```

<Warning>
  Do not expose API keys in client-side apps, prompts, screenshots, or shared logs. Route production calls through a secure backend.
</Warning>

## Recommended Learning Path for Agents

1. Start at [Introduction](/introduction) and [Architecture](/architecture)
2. Read [API Reference Introduction](/api-reference/introduction) for auth
3. Implement one flow from [Zap-In & Zap-Out tutorial](/tutorials/add-liquidity-api)
4. Expand to automation with [Auto Rebalance Bot](/tutorials/auto-rebalance-bot)

<Card title="Need help?" icon="headset" href="https://discord.gg/h8YDHtzmRU">
  Join the LP Agent community Discord for support.
</Card>