# Getting Started

This guide will walk you through everything you need to get up and running with Agistry: installing the SDK, discovering adapters, performing your first registry call, and executing off-chain logic.

***

#### 1. Log in to Agistry Hub

* Start by visiting **Agistry Hub** and logging in using your **Solana wallet** (e.g., Phantom or Backpack):

#### 2. Generate an API Key

1. Go to the **“API Keys”** section from the sidebar.
2. Click **“Create API Key”**.
3. Copy your key securely — you'll use it in your backend SDK calls.

> Each API key is tied to your account. You can rotate or revoke them at any time.

#### 3. Enable & Configure Adapters

In the **“Adapters”** tab:

1. Click **“Create Adapter”** or select from existing templates.
2. Choose an adapter type (e.g. `pdf-text-extractor`, `llm-analyzer`, `telegram-alert`)
3. Configure input fields, default values, and logic
4. Save and activate it

> You can visually define flow order later via UI or just call adapters directly via code.

#### 4. Install the SDK

```
npm install agistry
```

#### 5. Your First Adapter Execution

```typescript
import { AdapterExecutor } from 'agistry';

const agistry = new AdapterExecutor({
  baseUrl: 'https://api.agistry.ai',
  headers: {
    Authorization: `Bearer ${process.env.AGISTRY_API_KEY}`
  }
});

const result = await agistry.run(
  "Analyze this contract for risk. If risky, log and notify ops on telegram.",
  [
    "pdf-text-extractor",
    "llm-analyzer",
    "db-logger",
    "telegram-alert"
  ],
  {
    docUrl: "https://cdn.agistry.ai/uploads/nda.pdf"
  }
);

console.log("📊 Analysis Result:", result.analysis);
```

### Done. What Next?

* Explore and configure more adapters in **Agistry Hub**
* Chain them together into flows
* Add agents or LLM planners to automate tool usage
* Monitor execution logs and context in the dashboard


---

# Agent Instructions: 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:

```
GET https://docs.agistry.ai/framework/getting-started.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.