# Welcome to MIRARI

![MIRARI](/files/V3oXGmPiAQrjlnRG4YU9)

> *A mirror dashboard for agents that grow with you.*

**MIRARI** is an occult-themed **agent observatory**. You bind a Hermes Agent (or any OpenAI-compatible model endpoint) to MIRARI and it becomes the control room for that agent's evolving mind — chat, memory, skills, reflection, and metrics, all in one place.

Most chat UIs treat every session like the agent has amnesia. MIRARI does the opposite: it gives your agent a **persistent memory graph**, a **versioned skill library**, and a **reflection loop** that turns past conversations into a sharper system prompt. The agent doesn't just answer — it *learns*.

***

## What you get

* **Console** — chat with any bound agent, with conversations that persist.
* **Memory Atlas** — a living graph of facts, preferences, and context your agent remembers.
* **Skill Forge** — propose, test, promote, and version reusable skills.
* **Mirror Mode** — paste logs in, get strengths / weaknesses / a refined system prompt out.
* **Observatory** — a real-time dashboard of bindings, memory size, skills forged, and reflection cadence.
* **Templates** — share anonymized skills; import rituals forged by other oracles.
* **Tasks** — a lightweight workboard for the agent's todo list.

***

## The pitch in one image

![Hermes consulting the Mirror](/files/08E9DgyXvQoxcAuIHtpQ)

Hermes looks into the mirror. The mirror reflects what Hermes is becoming. That loop — bind, reflect, forge — is the whole product.

***

## Start here

* New to the project? → [What is MIRARI?](/entermirari-docs/getting-started/what-is-mirari.md)
* Want to wire up an agent right now? → [Quickstart](/entermirari-docs/getting-started/quickstart.md)
* Curious about the underlying graph and skill model? → [Core Concepts](/entermirari-docs/getting-started/core-concepts.md)


---

# 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://entermirari.gitbook.io/entermirari-docs/readme.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.