> For the complete documentation index, see [llms.txt](https://capture-os.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://capture-os.gitbook.io/docs/0.-capture-os.md).

# 0. Capture OS

This is the entry point to understanding Capture OS: what it is, how it’s built, and how you’re supposed to use it.

#### 0.1 What is Capture OS (ex-SpreadNet)?

**Capture OS** is a Solana arbitrage operating system.

At its core, it does one thing extremely well:

> **Continuously scan Solana DEXs for price inefficiencies and surface them in a clean, machine- and human-readable way — without ever touching your funds.**

The stack is split in layers:

* **Capture Engine**\
  The open-source detection core (the `capture` repo). It fetches quotes from multiple Solana DEXs/aggregators, normalizes them, calculates net spreads, filters noise, and outputs ranked opportunities in real time.
* **Capture Terminal**\
  The interface layer. This includes:
  * The **CLI terminal** you run locally.
  * The **hosted live feed** (web UI) that shows a real-time stream of opportunities and system stats.
* **Capture Bot** (optional product layer)\
  An automated execution engine that sits on top of Capture Engine, adds risk management and MEV-aware routing, and actually sends transactions. This is **not** part of the open-source repo; it’s the “automation on top”.

So the mental model:

* **Capture Engine** → finds edges
* **Capture Terminal** → shows edges
* **Capture Bot** → acts on edges

You can use any subset of these depending on who you are and what risk you want to take.


---

# 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 following URL with the `ask` and `goal` query parameters:

```
GET https://capture-os.gitbook.io/docs/0.-capture-os.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `build a script that syncs our docs to a CMS` lets GitBook tailor the answer to that use case.

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.