> For the complete documentation index, see [llms.txt](https://vector-privacy.gitbook.io/vector-privacy/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://vector-privacy.gitbook.io/vector-privacy/vector-messenger/features/viktor-ai-chatbot.md).
# Viktor (AI Chatbot)
Say hello to your new friend and ally in Vector, meet **Viktor**.
Viktor was designed as an optional, in-house AI chatbot to help you with certain tasks or any questions you may have. Viktor can be run locally and self-hosted, but at the moment cannot search the external web. Therefore, if you are trying to search for external links, he will be limited on his search queries and capabilities. In the future, Viktor will be trained specifically on Vector-related topics/subjects from basic troubleshooting to technical questions and can be seen as an information kiosk for anything related to Vector. He has quite the snarky personality, you've been warned.
### Get Started
[Add Viktor](https://vectorapp.io/profile/npub1gwfpm6l8fhn6rs83j8rjjnjgkdqv89chd2fdhy6zc2uvpuwf39vsfuxxee) as a friend or contact by clicking the "New Chat" button and add his official Contact ID (Nostr Public Key). You can immediately start chatting with him after you send the first message.
{% hint style="success" %}
Add Viktor: `npub1gwfpm6l8fhn6rs83j8rjjnjgkdqv89chd2fdhy6zc2uvpuwf39vsfuxxee`
{% endhint %}
### Developers
Viktor is based on an open-source LLM interface for Vector that anyone can use and developers can experiment with [here](https://github.com/VectorPrivacy/Vector-LLM). It supports both cloud-based models (via API) and fully local models, with everything running on your own machine. You can keep it private (limit your bot to only respond to you) or make it public, allowing anyone on Vector to interact with your bot, depending on your preferences. Viktor only stores the last 100 messages you have made with him. In future versions, users will be able to customize their interactions with Viktor more extensively, improving both the user experience and privacy control.
#### Features
* Vector-LLM can be used with Cloud AI (OpenAI, Anthropic, etc) or Local AI (on your own GPU or CPU) for extra privacy and full AI model control.
* The System Message (bot personality, traits, abilities), as well as Memory length are determined by the operator of the Chatbot via config file.
* You can view and hot-swap AI Models with a simple command: `!model` or `!model `.
---
# 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://vector-privacy.gitbook.io/vector-privacy/vector-messenger/features/viktor-ai-chatbot.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.