# Myros

<figure><img src="/files/EGYf6T3BzLwOKRyONFuv" alt=""><figcaption></figcaption></figure>

The internet has become the world’s largest archive of knowledge, yet most of that knowledge remains passive.

It sits inside documentation pages, websites, announcements, community chats, support threads, developer notes, and scattered internal resources. It exists, but it does not respond. It waits to be searched, interpreted, summarized, and understood.

For modern projects, this creates a growing problem.

Communities move faster than documentation.\
Users ask the same questions repeatedly.\
Builders lose time explaining what already exists.\
Teams struggle to keep knowledge accurate, accessible, and alive.

**Myros is built to change that.**

Myros is an open-source framework for launching real-time, knowledge-aware AI agents. She transforms static information into an interactive intelligence layer that users can speak to directly.

Instead of forcing people to search through fragmented sources, Myros allows projects, teams, businesses, and communities to deploy AI agents that retrieve, understand, and deliver relevant knowledge instantly.

Myros is not just another chatbot.

She is a launchpad for living knowledge agents.

Myros is an open-source AI agent framework designed to help projects create tailored, real-time knowledge agents from their own curated sources.

At its foundation, Myros enables an agent to connect with project-specific knowledge, retrieve live information from approved websites or sources, remember conversational context, and respond through familiar communication platforms such as Telegram.

The first release of Myros is focused on open-source adoption. Builders can self-host, modify, extend, and deploy Myros agents without relying on closed, centralized AI systems.


---

# Agent Instructions: 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:

```
GET https://myros.gitbook.io/bp/myros.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.