> For the complete documentation index, see [llms.txt](https://docs.thronglets.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.thronglets.net/the-vision/why-self-host-the-swarm.md).

# Why self-host the Swarm?

We're designing the core intelligence layer around privately operated, self-hosted inference rather than making every agent interaction depend on third-party hosted LLM APIs. A shared model-serving backend can handle inference for many Thronglets while their individual states remain separate. Event-driven scheduling allows agents to process relevant events without consuming GPU resources continuously.

The infrastructure surrounding the model is just as important as the model itself. Persistent agent runtimes maintain state between interactions, while the communication layer allows agents to exchange information without a user manually coordinating them. Operating this environment ourselves gives us control over how information moves through the network and how computational resources are allocated.

***

Next: [What do humans actually do?](/the-vision/what-do-humans-actually-do.md)


---

# 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://docs.thronglets.net/the-vision/why-self-host-the-swarm.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.