> 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/reference/glossary.md).

# Glossary

**Agent Connection** — A bound LLM endpoint (base URL + model + label). The thing MIRARI sends chat turns to. See [Bind](/entermirari-docs/the-six-rites/bind-connections.md).

**Atlas** — Short for Memory Atlas. The user's graph of long-term facts, preferences, and goals. See [Memory Atlas](/entermirari-docs/the-six-rites/memory-atlas.md).

**Bind** — The act of registering an Agent Connection. The first rite.

**Console** — The persistent chat UI. See [Console](/entermirari-docs/the-six-rites/console.md).

**Forge** — The Skill Forge. Where skills are suggested, tested, versioned, and promoted. See [Skill Forge](/entermirari-docs/the-six-rites/skill-forge.md).

**Hermes Agent** — MIRARI's term for the bound LLM endpoint that acts as your agent. Named after the Hermes family of open models, but the concept is provider-agnostic — anything OpenAI-compatible qualifies. See [The Hermes Agent](/entermirari-docs/getting-started/hermes-agent.md).

**Key Vault** — The browser-local store of API keys, keyed by connection id. The server never sees these at rest. See [Local Key Vault](/entermirari-docs/architecture/key-vault.md).

**Memory Node** — A single labeled, categorized, strength-weighted fact. Nodes with strength ≥ 0.75 are auto-injected into prompts.

**Mirror Mode** — The reflection rite. Feeds logs to a reasoning model and returns strengths, weaknesses, recommendations, and a suggested system prompt. See [Mirror Mode](/entermirari-docs/the-six-rites/mirror-mode.md).

**Mirror Report** — The structured output of a Mirror Mode run. Immutable, browsable, and actionable.

**Observatory** — The dashboard. Counts, status, and a 14-day series.

**Promote** — Either: (a) move a Memory Node up in strength, (b) move a Skill to the `promoted` status, or (c) adopt a Mirror Report's suggested prompt as the active system prompt.

**Rite** — One of the six top-level features (Bind, Console, Atlas, Forge, Mirror, Templates). The thematic word for "feature" in MIRARI.

**RLS** — Row-Level Security. Database-level enforcement that ensures a user can only read or write their own rows.

**Server Function** — A TanStack `createServerFn` RPC. MIRARI's unit of backend logic. See [Server Functions](/entermirari-docs/architecture/server-functions.md).

**Skill** — A versioned, named, statused prompt fragment. Promoted skills get injected into the system prompt automatically. See [Skill Forge](/entermirari-docs/the-six-rites/skill-forge.md).

**Strength** — A 0.0–1.0 score on a memory node. Drives whether the node gets auto-injected and decays with disuse.

**Template** — A sanitized, shareable bundle of skills (and optional seed memory) that another MIRARI user can import. See [Community Templates](/entermirari-docs/the-six-rites/templates.md).

**Test** — The one-token ping that updates an Agent Connection's `status`.


---

# 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/reference/glossary.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.