> For the complete documentation index, see [llms.txt](https://entermirari.gitbook.io/entermirari-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://entermirari.gitbook.io/entermirari-docs/the-six-rites/observatory-tasks.md).

# VI. Observatory & Tasks

## Observatory (Dashboard)

The Observatory is MIRARI's home page after sign-in — a single screen that tells you, at a glance, **whether your agent is alive and learning**.

It pulls counts and a 14-day series straight from the database:

```ts
type Stats = {
  connections: number;       // bindings total
  online: number;            // status === "online"
  conversations: number;
  messages: number;
  memory: number;            // memory_nodes count
  skills: number;            // all skills
  promoted: number;          // status === "promoted"
  mirrors: number;           // mirror_reports count
  templates: number;
  tasks: number;
  tasksComplete: number;
};

type SeriesPoint = { day: string; messages: number; skills: number };
```

The page renders:

* **Tiles** for each scalar.
* **An area chart** (Recharts) of `messages` and `skills` over the last 14 days.
* **Status row** for every bound Hermes Agent — last ping, last error.

Use it as your "is the loop still turning?" check.

## Tasks

The Tasks page is a lightweight workboard. Three statuses: `pending`, `in_progress`, `done`. Each task has a title, an optional description, an optional `connection_id` (so you can scope a task to a specific Hermes Agent), and timestamps.

```ts
type Task = {
  id: string;
  user_id: string;
  title: string;
  description: string | null;
  status: "pending" | "in_progress" | "done";
  connection_id: string | null;
  created_at: string;
  updated_at: string;
};
```

Tasks intentionally do **not** auto-execute. They are a working memory for *you*, the operator — "things the agent and I should chip away at this week" — surfaced where the rest of MIRARI lives instead of in a separate tool.

Mirror reports can produce tasks from their `recommendations` list with one click, which closes a nice loop: reflect → tasks → forge → reflect again.


---

# 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:

```
GET https://entermirari.gitbook.io/entermirari-docs/the-six-rites/observatory-tasks.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.