> 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/solution.md).
# Solution
YveChat is the sovereign AI workspace where your models, conversations, compute, credentials, and identity remain under your control. Easily run local AI on your own hardware, keep conversations on your own disk, and move across models from one workspace.
Your models. Your machine. Your workspace.
***
#### Vision
A world where the record of how a person thinks belongs to that person.
#### Mission
Deliver a workspace where frontier models, local models, and agent tooling operate under the user's own keys, on the user's own infrastructure, behind the user's own signature.
***
### Core Features
#### 1) Every major model, one thread
Frontier hosted models and locally served open-weight models appear in a single conversation. Switching between them is a keystroke, and context carries across the switch.
#### 2) Bring your own keys
A local model needs no credential of any kind, and that path is available today. Credentials for configured tools stay inside the Engine process on the user's machine. Full hosted-provider credential management is planned, and YveChat takes zero margin on inference in every case.
#### 3) Local inference as a first-class path
Ollama-served models run entirely on the user's hardware. For those conversations, no key exists, no provider is contacted, and no network request leaves the machine.
#### 4) Self-hosted data
Conversations persist to a SQLite database that YveChat Engine manages on the user's own disk. The file sits on hardware the user owns, and deletion removes the data. A user-configurable storage location is planned.
#### 5) Wallet-native identity
Access is granted by a signature. There is no account record held by YveChat to suspend, recover, or leak.
#### 6) A tool gateway with a visible boundary
Search, reading, and retrieval run with disclosed activity and clickable citations. Any action that writes, sends, purchases, or authenticates waits for explicit confirmation. Details in [Tool Gateway](/wp/capabilities/tool-gateway.md).
***
### The Unique Position
#### 1) Sovereignty is the product
Competing workspaces treat custody as a setting. YveChat treats it as the organizing principle, and accepts the resulting constraints, including the requirement that users install a local component.
#### 2) Zero inference margin, permanently
The business model earns from software, tooling, and network participation. It stays clear of the inference bill entirely, which is what makes bring-your-own-keys durable.
#### 3) Provider neutrality by construction
A normalized provider layer treats OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible endpoint as peers. The workspace outlives any single provider's pricing or policy.
***
### How It Fits Together
```mermaid
graph TD
U["You"] --> W["YveChat Workspace"]
W --> B["YveChat Engine
on your machine"]
B --> L["Local models
Ollama, ComfyUI"]
B --> T["Tool gateway
web search with citations"]
B --> D[("Conversations
on your own disk")]
```
The workspace renders the interface. The Engine holds the secrets, reaches the runtimes, and keeps the conversation on the user's machine. Architecture detail is in [Architecture](/wp/architecture.md).
***
One surface for the whole model landscape.
Held entirely by the person using it.
---
# 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/solution.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.