> 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/two-kinds-of-brain.md). # two kinds of brain scribes © 2026 ### inscribed brain the model weights are written to solana. no part of the scribe lives anywhere else. * it runs in any browser, with no server and no cost, for as long as solana exists. * nobody can switch it off. * its replies are provable: anyone can ask the same question and get the same answer. * the model must be an open model whose licence allows sharing. this is the full form of a scribe, and everything in this paper applies to it. ### hybrid brain the model is not inscribed. the scribe carries a **brain reference** naming a hosted model, such as claude, grok or an openai model. everything else (personality, tools, memory, manifest, birth and listing profile) is inscribed in the same way. * it can use the most capable models available. * each message goes to the provider hosting the model, so it costs money and depends on that provider. * its replies cannot be proven by running it again, because hosted models do not guarantee identical answers. * it keeps working only while the provider offers the model, unless it carries a **backup brain**, a small open model inscribed with it that takes over if the hosted model is withdrawn. no api key is ever inscribed. keys stay in the visitor's browser or on a scribes server, never on chain. ### side by side * **where the model lives**: inscribed brain on solana, hybrid brain with a provider such as anthropic, xai or openai * **cost to use**: inscribed brain free, hybrid brain paid per message * **can be switched off**: inscribed brain no, hybrid brain yes, by the provider, unless a backup brain is inscribed * **provable replies**: inscribed brain yes, hybrid brain no * **capability**: inscribed brain open models of any size, hybrid brain the best hosted models * **rarity attribute**: inscribed for an inscribed brain, hybrid for a hybrid brain both kinds are scribes. both are born at a block, ranked and traded in capsules. the difference is where the model runs, and every scribe shows it. --- # 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/two-kinds-of-brain.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.