# Welcome to Quicksilver

[**Quicksilver AI**](https://github.com/iotexproject/quicksilver) is a modular framework for building intelligent agents that can **think**, **fetch data**, and **take real-world actions** — all powered by Large Language Models (LLMs) and connected APIs.

## What Is It?

Quicksilver AI lets you create and deploy AI agents that can:

* **Understand user queries** using popular LLMs (e.g., OpenAI, Claude, DeepSeek)
* **Retrieve real-time data** from external APIs, blockchains, or DePIN networks
* **Trigger actions** — like sending transactions, posting to social platforms, or calling services

Quicksilver agents can work autonomously or in collaboration with other agents and humans.

## What Can You Do with Quicksilver?

* **Develop custom agents**: Define your agent’s personality, logic, and access to APIs.
* **Deploy agents to Quicksilver AI**: Publish them for others to use via chat or API.
* **Monetize**: Set pricing and earn when people use your agent.
* **Integrate anywhere**: Use the QuickSilver API to plug your agent into your own apps, workflows, or UIs.

## How It Works

QuickSilver gives you a full toolkit:

* **A visual portal** for managing and publishing agents
* **Support for vector databases** (Qdrant, Pinecone), streaming APIs, smart contract clients
* **Lightweight SDKs** for rapid development and extensibility

## Get Started

Head over to the Getting Started section to learn how to use Quicksilver, build and publish your first QuickSilver agent — no complex setup required.

<a href="/pages/3mvLP4UraYRSrCzXGzvg" class="button primary">Create your first Agent</a>


---

# 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.iotex.io/quicksilver/welcome-to-quicksilver.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.