> For the complete documentation index, see [llms.txt](https://basket-fund.gitbook.io/basket.fund-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://basket-fund.gitbook.io/basket.fund-docs/creators-and-rebalancing/creating-a-basket.md).

# Creating a basket

Creators are the reason baskets exist.

A basket is not generated by an algorithm in the MVP. It is created and managed by a person who has a view on the market and wants to express it publicly.

Creators can launch one public basket, write a thesis, choose up to 10 tokens, set weights, and update the basket over time. The one-basket limit is intentional for the MVP. It keeps the product focused and makes each creator’s basket easier to evaluate.

A creator starts by logging in with X.

From there, they create a basket, select tokens across the supported networks, assign weights, and write a required whole-basket thesis. Token-level notes can be added too, but the main thesis matters most.

A basket should answer a clear question:

Why should this group of assets exist together?

Good baskets are not just collections of popular tickers. They have a reason behind the selection, a view on the market, and enough clarity for users to understand what they are following.

After launch, the basket becomes visible to users.


---

# 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 current page URL with the `ask` query parameter:

```
GET https://basket-fund.gitbook.io/basket.fund-docs/creators-and-rebalancing/creating-a-basket.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.