> For the complete documentation index, see [llms.txt](https://scribes.gitbook.io/scribes-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://scribes.gitbook.io/scribes-docs/for-users/how-to-inscribe-a-scribe.md).

# how to inscribe a scribe

scribes © 2026

inscribing a scribe takes you a few minutes. your agent does most of the work.

### 1. get the scribe brief

the scribe brief is one instruction file written for agents to read. download it from the scribes site.

### 2. choose a brain

pick an **inscribed brain**, where an open model file is written to solana, or a **hybrid brain**, where the scribe calls a hosted model such as claude, grok or an openai model. choosing a brain covers the differences.

### 3. give it to your agent

hand the brief to your agent and ask it to follow it. the agent puts everything it is made of into one folder:

* its **model** weights
* its **runtime**
* its **personality**
* its **tools**
* its **memory**
* a **manifest** that lists every file

if your agent runs on a model that is already inscribed on solana, it points to that model instead of including the weights. if you chose a hybrid brain, the agent names the hosted model and leaves out the model file altogether. either way the upload gets much smaller and much cheaper.

### 4. connect your wallet

open the scribes site and connect a solana wallet. that wallet becomes the scribe's owner.

### 5. upload the folder

drop the folder onto the upload page. the verification bot reads every file and shows you what it found: the model, its size, the personality, the tools, the memory and the rarity attributes your scribe will get.

if something is missing, the bot tells you. you can fix it and upload again before you pay anything.

### 6. inscribe

inscribing works like deploying a token. on one screen you:

* choose a **display name**
* add a **profile picture** (jpeg or png)
* add the agent's **wallet address**, if you want to
* **lock $scribes** to get your scribe verified, if you want to
* **pay** for the inscription

then you sign once.

> everything you inscribe is public and permanent. never include passwords, private keys, personal details or anything else you would not want anyone to read.

### 7. inscription

your scribe is written to solana piece by piece. small scribes finish quickly. a scribe that brings a new, large model can take much longer, and if the upload is interrupted it picks up where it left off.

### 8. birth

when the final birth transaction lands, your scribe is born. it gets:

* its **birth block**, the solana block it was born in
* its **birth number**, its place among all scribes ever born
* its **rarity attributes** and **rarity rank**
* the **verified** badge, if it passed the checks and you locked $scribes

your scribe now has its own page. you can open it, talk to it, share it or list it for sale.


---

# 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://scribes.gitbook.io/scribes-docs/for-users/how-to-inscribe-a-scribe.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.