> For the complete documentation index, see [llms.txt](https://yvechat.gitbook.io/wp/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://yvechat.gitbook.io/wp/resources/faq.md).
# FAQ
The same questions, answered briefly at yvechat.xyz
***
### For Users
#### What does sovereignty actually mean here?
Four things, each verifiable. Tool credentials stay inside YveChat Engine on your machine, and a local model needs no credential at all. Conversations persist to a SQLite database on your own disk. Your identity is a profile held locally by YveChat Engine, opened with a local account or an optional wallet signature. And a locally served model produces answers without contacting anyone. The full definition, including what each layer costs you, is in [Sovereignty Model](/wp/sovereignty-model.md).
#### Do I have to install something?
For local models, yes. Either the desktop application or the lightweight YveChat Engine. Browser constraints make a pure hosted page unreliable for reaching local runtimes, and the reasons are documented with sources in [YveChat Engine](/wp/architecture/engine.md).
#### Are local models as good as the frontier ones?
No. The gap is measurable and it is stated with a source in [Limitations](/wp/product-scope/limitations.md). Local inference serves work where custody matters more than raw capability. Hosted-provider access is Planned, and it will let you reach larger models with your own credentials.
#### What does YveChat charge for inference?
Nothing. A local model runs on hardware you own, at the cost of your own electricity and time. When hosted-provider support ships you will pay your provider directly at their price. The zero-margin commitment is permanent.
#### What happens if I lose my wallet?
Wallet authentication is optional, and a local account provides the same access to the same workspace. Choosing a local account means a lost wallet costs you nothing.
For a profile created by wallet signature, that wallet identifies the profile, so custody of the wallet matters. Your conversations remain in the database on your own disk in either case.
***
### For Self-Hosters
#### What am I responsible for?
Provisioning storage, backups, TLS renewal, and updates. Certificate lifetimes are shortening, so unattended ACME automation is a requirement. Sources are in [Limitations](/wp/product-scope/limitations.md).
#### Does self-hosting reduce my compliance burden?
It increases it. Under GDPR, whoever determines the purposes and means of processing is the controller. A self-hoster processing other people's personal data becomes that controller and inherits the full obligation set. Sovereignty transfers responsibility along with control.
#### Can I point YveChat at a model server on another machine?
Not initially. Ollama binds to loopback by default, so the Engine and the runtime are co-resident in the first release. Remote runtime configuration is a later, explicit option.
***
### For Builders
#### Can I connect my own MCP servers?
MCP support is Planned. No implementation exists today, and MCP server installation sits outside the current trust boundary by design. The intended contract, including per-tool permissions and treating tool descriptions as untrusted, is described in [Tool Gateway](/wp/capabilities/tool-gateway.md).
#### Which runtimes can I target?
Ollama is Available and fully supported. OpenAI-compatible endpoints and vLLM are Experimental and configured manually. Compatibility is negotiated per backend, because OpenAI-compatible describes a request shape, and feature parity varies. See [Runtimes](/wp/architecture/runtimes.md).
#### How does the marketplace work?
Builders publish agents, prompt packs, and MCP configurations, set their own prices, and receive revenue share with a defined protocol take. It arrives in the Network era. See [Utilities](/wp/yve/utilities.md).
***
### For Token Holders
#### What creates demand for `$YVE`?
Five utilities arriving one per era: the Sovereign Pass, gateway credits, marketplace settlement, compute settlement, and governance. None of them touches the price of inference. See [Utilities](/wp/yve/utilities.md).
#### If YveChat takes zero margin on inference, where does revenue come from?
The scaling tier, gateway usage, deployment support, and marketplace take. A portion of fiat revenue recycles into buybacks. See [Revenue](/wp/yve/revenue.md).
#### When is the token generation event?
Unannounced. `$YVE` has not been generated, no contract is deployed, and no sale is open. Anything currently offering `$YVE` is fraudulent. See [Verified Links](/wp/resources/verified-links.md).
#### Is the supply final?
The model in [Tokenomics](/wp/yve/tokenomics.md) is provisional and subject to the final economic and legal structure.
---
# 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 dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://yvechat.gitbook.io/wp/resources/faq.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.