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

# Introduction

Sigrex is a trading automation platform that sits between your ideas and the market.

It provides a complete toolkit to generate, process, and execute trades across major CEXs, Uniswap (native Web3), and Polymarket (beta). Whether you want to use it as a pure execution engine, a signal generator, or a completely autonomous trading system, Sigrex adapts to your workflow.

> **Talk to Sigrex from any AI assistant.** The MCP server plugs into Claude, ChatGPT, Cursor or other compatible clients. Create and manage strategies through chat. [**Setup guide →**](https://docs.sigrex.io/more/mcp-server)

<details>

<summary>🌐 Supported Exchanges</summary>

<table><thead><tr><th width="130">Exchange</th><th width="124.6666259765625">Type</th><th width="81.6666259765625" data-type="checkbox">Spot</th><th width="101.6666259765625" data-type="checkbox">Futures</th><th width="126.333251953125">More</th><th width="183.6668701171875">API ID</th></tr></thead><tbody><tr><td><a href="https://alpaca.markets">Alpaca</a> </td><td>CEX</td><td>true</td><td>false</td><td>No Paper trading</td><td>Spot: <code>1</code></td></tr><tr><td><a href="https://www.binance.com">Binance</a></td><td>CEX</td><td>true</td><td>true</td><td>USD-M only</td><td><p>Spot: <code>2</code> </p><p>Futures: <code>3</code></p></td></tr><tr><td><a href="https://www.bitget.com/">Bitget </a></td><td>CEX</td><td>true</td><td>true</td><td>USD-M only</td><td><p>Spot: <code>13</code> </p><p>Futures: <code>14</code></p></td></tr><tr><td><a href="https://www.mexc.com">MEXC</a> </td><td>CEX</td><td>true</td><td>true</td><td>USD-M only</td><td><p>Spot: <code>4</code> </p><p>Futures: <code>16</code></p></td></tr><tr><td><a href="https://www.gate.io">Gate.io</a> </td><td>CEX</td><td>true</td><td>true</td><td>USD-M only</td><td><p>Spot: <code>8</code> </p><p>Futures: <code>9</code></p></td></tr><tr><td><a href="https://www.kraken.com">Kraken</a> </td><td>CEX</td><td>true</td><td>true</td><td></td><td><p>Spot: <code>6</code> </p><p>Futures: <code>7</code></p></td></tr><tr><td><a href="https://app.hyperliquid.xyz/trade/BTC">Hyperliquid </a></td><td>CEX</td><td>true</td><td>true</td><td>USDC only</td><td><p>Spot: <code>11</code> </p><p>Futures: <code>12</code></p></td></tr><tr><td><a href="https://app.uniswap.org/">Uniswap</a></td><td>DEX</td><td>true</td><td>false</td><td>Polygon, Arbitrum</td><td>Spot: <code>10</code></td></tr><tr><td><a href="https://polymarket.com/">Polymarket</a></td><td>PREDICTION</td><td>true</td><td>false</td><td></td><td>Spot: <code>15</code> </td></tr><tr><td><a href="https://outcome.xyz/">Outcome.xyz</a></td><td>PREDICTION</td><td>true</td><td>false</td><td></td><td>Spot: <code>17</code> </td></tr></tbody></table>

</details>

<details>

<summary>🤖 Supported LLM Provider</summary>

| Provider                                               | API ID               |
| ------------------------------------------------------ | -------------------- |
| [Google Gemini](https://gemini.google.com/)            | `1`                  |
| [OpenAI](https://openai.com/)                          | `2`                  |
| [DeepSeek](https://www.deepseek.com/)                  | `3`                  |
| [Claude](https://claude.ai/)                           | `4`                  |
| [Mistral](https://mistral.ai/)                         | `5`                  |
| [Cohere](https://cohere.com/)                          | `6`                  |
| [Grok (xAI)](https://grok.com/)                        | `7`                  |
| [Alibaba Cloud (Qwen)](https://www.alibabacloud.com/)  | `8`                  |
| [~~Perplexity~~](https://www.perplexity.ai/)           | ~~`9`~~ (suspended)  |
| [Moonshot AI (Kimi)](https://www.moonshot.ai/)         | `10`                 |
| [Z.ai](https://chat.z.ai/)                             | `11`                 |
| [MiniMax](https://www.minimax.io/)                     | `12`                 |
| [Nvidia](https://build.nvidia.com/)                    | `13`                 |
| [Nous Research](https://portal.nousresearch.com/)      | `14`                 |
| [OpenRouter](https://openrouter.ai/)                   | `15`                 |
| [Xiaomi (MiMo)](https://mimo.xiaomi.com/)              | ~~`16`~~ (suspended) |
| [Groq](https://groq.com/)                              | `17`                 |
| [Cerebras](https://www.cerebras.ai/)                   | `18`                 |
| [SiliconFlow](https://cloud.siliconflow.com/)          | `19`                 |
| [Sambanova](https://sambanova.ai/)                     | `20`                 |
| [Meta AI](https://developer.meta.com/ai/)              | `21`                 |
| [Vercel](https://vercel.com/ai-gateway)                | `22`                 |
| [Cheaper Inference](https://www.cheaperinference.com/) | `23`                 |

</details>

### A few things you can do

* ⚡️ Execute from Anywhere: Send orders from TradingView, your own custom scripts, or external bots, and let Sigrex handle the execution.
* 🤖 Deploy AI Agents: Let AI agents generate reports or trade directly for you.
* ⚙️ Generate Signals: Build and run strategies for signal generation natively inside Sigrex.
* 🔗 Build Event-Driven Reactions: Create workflows that respond instantly to any incoming data.
* 🤝 Collaborate & Share: Split the exact same orders or events seamlessly across multiple users and friends.

### How it works

The system is organized into clear, flexible layers to give you deep customization.

```mermaid
graph TD

    %% Define the distinct layers using subgraphs
    subgraph Internet Layer
        OS(Outer space)
    end
    
    subgraph Data Processing Layer
        DH(Data hook)
    end
    
    subgraph Strategy Layer
        RS1(Reaction Strategies)
        RS2(Reaction Strategies)
        RS3(Reaction Strategies)
        SS(Simple Strategies)
    end
    
    subgraph Signal Processing Layer
        BH(Bot hook)
    end
    
    subgraph Execution Layer
        SB1(Signal Bots)
        SB2(Signal Bots)
        SB3(Signal Bots)
        SB4(Signal Bots)
    end

    %% Define the connections between nodes
    OS --> DH
    OS --> BH
    
    DH --> RS1
    DH --> RS2
    DH --> RS3
    
    RS1 --> BH
    RS2 --> BH
    RS3 --> BH
    SS --> BH
    
    BH --> SB1
    BH --> SB2
    BH --> SB3
    BH --> SB4

    %% Apply a clean, minimalist style similar to the image
    classDef default fill:#ffffff,stroke:#333333,stroke-width:1px,color:#000000;
```

**Simple Strategies** run on their own:

* [**Code Strategies**](/strategies/code.md) — Write sandboxed JavaScript equipped with rich [helper functions](/strategies/code.md#available-variables) and HTTP request capabilities. Because they have full access to the [Sigrex API](https://docs.sigrex.io/api-reference/), a single strategy can even manage your other strategies.
* [**LLM Sessions**](/strategies/llm-session.md) — Periodically running AI agents. You control the [prompts](/strategies/llm-session/signal-generation.md#template-variables) and equip the LLM with powerful [tools](/strategies/llm-session/signal-generation.md#llm-tooling-reference) so it can analyze, decide, trade autonomously and even manage your other strategies.

**Reaction Strategies** ([Code](/reaction/code-reaction.md) or [LLM](/reaction/llm-reaction.md)) don’t run by themselves. They wait for an **event**. Any HTTP payload you send to a [**Data Hook**](/reaction/data-webhook.md) becomes an event. You can even share that [**Data Hook**](/reaction/data-webhook.md) with friends so multiple people can react to the same incoming data.

Everything eventually flows into the [**Bot Hook**](/getting-started/webhook.md), which routes the final signals to your **Signal Bots** that execute on the exchanges.

This design makes Sigrex extremely flexible: pure execution layer, fully autonomous agents, event-driven workflows, multi-user collaboration, and deep customization through both code and AI.

### What's Next?

* 👉 [Master Bot Webhooks](/getting-started/webhook.md) — Learn how to [format payloads](/getting-started/signal-payload-format.md) and route your final signals.
* 👉 [Integrate Exchange APIs](/cex-signal-bot/exchange-api-key.md) — Securely link your CEX accounts.
* 👉 [Explore Signal Bots](/cex-signal-bot/exchange-api-key.md) — Set up listeners to execute trades on your connected platforms.
* 👉 [Discover AI Trading](/strategies/llm-session.md) — See how LLM Sessions can analyze and trade autonomously for you.

Happy building! 🛠️

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td>Code Strategy</td><td></td><td><a href="/strategies/code.md">Code</a></td></tr><tr><td>LLM Session</td><td></td><td><a href="/strategies/llm-session.md">LLM Session</a></td></tr><tr><td>Reactions</td><td></td><td><a href="/reaction/data-webhook.md">Reaction</a></td></tr></tbody></table>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.sigrex.io/readme.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 `automate deployments from our CI pipeline` 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.