> For the complete documentation index, see [llms.txt](https://docs.deryve.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.deryve.xyz/introduction.md).

# Introduction

Deryve is a cloud-native autonomous agent trading platform.

Configure an agent for crypto, equities, ETFs, and commodities. Deryve executes through Lighter’s on-chain order book on Robinhood Chain. You can also place and manage manual trades when needed.

Select an agent and define its limits. Deryve runs analysis, execution, position management, and exits in the cloud.

### How Deryve works

1. Deryve reads market data and calculates technical indicators.
2. The intelligence pipeline classifies the market regime.
3. Your selected agent produces a structured trading decision.
4. The risk engine validates each eligible decision before execution.

Agentic trading is Deryve’s primary experience. An enabled agent continues operating after you close the app or turn off your device. It analyzes markets, opens qualifying positions, manages risk, and closes positions automatically.

{% hint style="warning" %}
Perpetual futures are high risk. Leverage can amplify losses and may result in liquidation. AI analysis is not investment advice and does not guarantee performance.
{% endhint %}

### Documentation map

* **Platform** covers markets, price data, charts, and wallet metrics.
* **Trading** covers agentic execution, optional manual orders, positions, funding, and performance tracking.
* **AI agent** explains agent selection, analysis, risk controls, and cloud workflows.
* **Developers & resources** covers integrations, API behavior, status, and support.

### Key principles

**On-chain execution.** Trades settle through Lighter’s central limit order book.

**Cloud-native automation.** Enabled agents run in Deryve’s cloud infrastructure. They do not depend on your browser or device remaining online.

**User control.** You can place manual orders and manage positions directly at any time.

**Hard risk boundaries.** The risk engine can reject or resize a decision. Custom instructions cannot override its controls.

### Get started

1. Connect a supported wallet and review available margin.
2. Select an agent model that fits your preferred strategy.
3. Set maximum size, leverage, protection, and daily loss boundaries.
4. Enable the agent and monitor its activity from any device.

Continue with the **Platform** group to understand available markets and data behavior.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.deryve.xyz/introduction.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.