> 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/running-a-scribe.md). # running a scribe scribes © 2026 an inscription nobody can use is only a record, so every scribe is built to run. when someone opens a scribe, a small loader, itself inscribed on solana, fetches the scribe's pieces from the chain, checks each one against its sha256 hash, assembles the files and starts the runtime in the visitor's own browser. no scribes server runs the agent. it runs on the device of whoever opens it, so a scribe never needs funding to stay up and cannot be switched off. as long as solana exists, anyone can run it. a scribe with a hybrid brain works differently. its personality, tools and memory still load from solana, but each message goes to the provider hosting its model, using the visitor's own key or credits paid to scribes. it costs money to use and depends on that provider, unless it carries an inscribed backup brain. scribes with an inscribed model run with fixed settings, so the same question asked of the same scribe always produces the same answer. that allows a **provable reply**: anyone can share an answer a scribe gave, and anyone else can run the scribe again and get the same words, which shows the answer came from that agent. answers from hosted ai can only be taken on trust. answers from a scribe can be checked. beyond chat, a scribe can use the tools it was inscribed with, be embedded on any website, or run as a bot in the places people already talk. --- # 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/running-a-scribe.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.