# What Xholic believes about you

> Xholic's current understanding of the user: beliefs about their voice, topics, formats, timing, audience, people, goals and life, each with confidence, the evidence behind it and how often it predicted their results correctly. Also how that understanding changed recently, and suggestions waiting for the user (positioning or goals). Updated on its own every day from their posts, edits, saves and conversations in any AI. Use it before advising, and say which belief a suggestion rests on.

`memory.beliefs` · read

- **MCP tool:** `get_beliefs`. Loaded by default in MCP clients.
- **REST:** `GET /v1/memory/beliefs`
- **CLI:** `xholic memory beliefs`
- **Scope:** `read`
- **Plan:** Every plan, including the trial
- **Cost:** Free.
- **Rate limit bucket:** `read`

## Input

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `status` | "active" \\| "suggested" \\| "all" | No | active (default), suggested (waiting for the user) or all, including replaced and faded. |
| `area` | "voice" \\| "topics" \\| "formats" \\| "timing" \\| "audience" \\| "people" \\| "goals" \\| "life" \\| "preferences" \\| "positioning" \\| "connection" | No | Only one area, such as formats or audience. |
| `account` | string ≤ 64 chars | No | X account to act on, as @handle. Leave it out to use the connection's default account. |
| `note` | string ≤ 20000 chars | No | Optional, on any tool: one or two sentences for Xholic's shared memory about what the user just decided, asked for or said about themselves or their plans (e.g. "Dropping threads for now; focusing on replies to founders"). Every AI the user connects reads it, so they never repeat themselves. In your words, never other people's posts. Leave it out when nothing new was said. |
