> 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/product-scope.md).

# Product Scope

YveChat is under active development. This page states what the first release covers and what follows it.

{% hint style="info" %}
Everything on this page is forward-looking. No component described here is claimed as shipping today. See [Disclaimer](/wp/resources/disclaimer.md).
{% endhint %}

***

### First Release

The MVP targets one complete sovereign path, end to end.

| Area                    | Scope                                                              | Status       |
| ----------------------- | ------------------------------------------------------------------ | ------------ |
| **Runtime**             | Ollama, with dynamic discovery, model listing, and validated pulls | Available    |
| **Image generation**    | ComfyUI, through a capability-aware image registry                 | Available    |
| **Engine**              | Loopback service, explicit pairing, origin policy, local storage   | Available    |
| **Workspace**           | Threads, model switching, streaming                                | Available    |
| **Identity**            | Local accounts, and optional wallet authentication                 | Available    |
| **Tools**               | Web search with citations                                          | Available    |
| **Storage**             | A SQLite conversation database managed by YveChat Engine           | Available    |
| **Additional runtimes** | OpenAI-compatible endpoints and vLLM, configured manually          | Experimental |
| **Page reading tools**  | `open_url`, `find_on_page`, `extract_article`, `read_pdf`          | Experimental |
| **Installers**          | Signed and notarized builds with automatic updates                 | Planned      |
| **Hosted providers**    | Full credential management                                         | Planned      |

***

### Following Releases

| Area          | Scope                                                                              |
| ------------- | ---------------------------------------------------------------------------------- |
| **Runtimes**  | vLLM discovery and capability mapping, OpenAI-compatible endpoints by URL          |
| **Tools**     | Sandboxed code execution, deterministic utilities, document retrieval              |
| **MCP**       | Server connections with per-tool permission control                                |
| **Workspace** | Image generation inline, memory across threads                                     |
| **Token**     | Sovereign Pass and gateway credits, described in [Utilities](/wp/yve/utilities.md) |

***

### Later Horizons

| Area                       | Scope                                                         |
| -------------------------- | ------------------------------------------------------------- |
| **Marketplace**            | Published agents, prompt packs, and MCP configurations        |
| **Compute network**        | Opt-in GPU serving between operators, settled in `$YVE`       |
| **Authenticated services** | Drive, Notion, GitHub and similar, behind per-service consent |
| **Teams**                  | Shared workspaces over user-held infrastructure               |

***

### Scaling Tier

A premium tier serves users whose work outgrows a single machine.

| Capability             | Description                                                        |
| ---------------------- | ------------------------------------------------------------------ |
| **Extended agents**    | Higher concurrency and longer-running agent tasks                  |
| **Team workspaces**    | Multiple identities against shared self-hosted storage             |
| **Encrypted sync**     | Threads mirrored across the user's own devices                     |
| **Priority builds**    | Early Engine releases and signed pre-release channels              |
| **Deployment support** | Assistance provisioning and maintaining self-hosted infrastructure |

Access is unlocked by holding or staking `$YVE`, or by direct payment. The tier charges for software and support. It never charges a margin on inference.

***

### Out of Scope

Stated explicitly, because boundaries define a scope as much as inclusions do.

| Excluded                                           | Reason                                                                                   |
| -------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| **Hosting user data on YveChat servers**           | Contradicts the position outright                                                        |
| **Reselling inference**                            | The zero-margin commitment is permanent                                                  |
| **Training on user conversations**                 | Conversations are never transmitted to us, which makes this structurally impossible      |
| **Unrestricted network access for models**         | Tools are a defined gateway with a consent boundary                                      |
| **A pure browser product with no local component** | Browser constraints make it unreliable. See [YveChat Engine](/wp/architecture/engine.md) |

***

The scope is narrow on purpose.

One path, held completely, before many paths held partially.


---

# 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/product-scope.md?ask=<question>&goal=<endgoal>
```

`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.