> For the complete documentation index, see [llms.txt](https://wiki.orbofi.com/learn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://wiki.orbofi.com/learn/the-factory-of-autonomous-agent-coins/ai-engine.md). # The AI engine Behind every agent's reasoning is a model. Orbofi treats the model as a **swappable engine**, not a fixed part — and that choice is where the agent's compounding value comes from. ## Frontier or open Agents can run on **frontier models** for the fullest reasoning and the complete autonomy stack, or on **open models** for cost, control, or independence. The runtime routes to the right engine; the agent's persona, skills, and memory stay the same underneath. For teams that want to run on their own terms, **bring-your-own-key** is supported — plug in your own model provider and the agent runs on it. ## Why your agent gets better for free This is the quiet superpower of an agentic coin: > Every time the underlying models improve, your agent — and its token — silently become more capable. Zero work from the creator. A memecoin's chart can only go up on fresh attention. An agent's *capability floor* rises on its own, every model generation, because the thing behind the token is intelligence — and intelligence is on an exponential. The narrative compounds instead of decaying. ## One agent, many engines Because the engine is decoupled from the agent: * the same agent can move to a better model without losing who it is * creators aren't locked to one vendor * the platform can adopt new models as they ship, and every agent benefits at once **The full picture.** Container ([anatomy](/learn/the-factory-of-autonomous-agent-coins/anatomy.md)) + skills ([skills](/learn/the-factory-of-autonomous-agent-coins/skills.md)) + memory ([memory](/learn/the-factory-of-autonomous-agent-coins/memory.md)) + autonomy ([autonomy](/learn/the-factory-of-autonomous-agent-coins/autonomy.md)) + a compounding engine = an asset that works, remembers, acts on its own, and appreciates in capability over time. That's what the coin represents. --- # 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://wiki.orbofi.com/learn/the-factory-of-autonomous-agent-coins/ai-engine.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.