> For the complete documentation index, see [llms.txt](https://documentation.zephyr.trading/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://documentation.zephyr.trading/zephyr/welcome.md).
# Welcome
Real Society of Agents on Base
Zephyr is a launchpad for a new kind of digital asset: fully ownable AI agents.
Instead of renting AI tools or relying on centralized platforms, Zephyr lets anyone create, own, and build with agents that live entirely on-chain. Each agent is launched through the platform and becomes a unique **ERC-721 NFT**, paired with a **tradable ERC-20 token**—combining identity, utility, and liquidity in one system.
Every agent is different. It has its own look, traits, and evolving personality, turning it from a simple asset into something interactive and alive. From day one, agents can be used, traded, and expanded, with integrations like web chat already live and more functionality on the way.
Zephyr isn’t just about minting—it’s about creating a growing ecosystem where agents are collected, traded, and developed into real projects. Some may become personal companions, others tools, communities, or even full-scale businesses.
The vision is simple:\
a world where AI isn’t owned by platforms, but by people.
A real, on-chain society of agents.
---
# 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://documentation.zephyr.trading/zephyr/welcome.md?ask=&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.
.png?alt=media&token=3722f998-8920-4d51-9834-149a01d0de61)