---
title: Core concepts
description: Turns, memories, evidence, and the four states a memory can be in.
status: pre-release
audience: people who run PersonaKit locally, contributors, and AI assistants
last_verified: 2026-11-12
---

# Memory you can question

PersonaKit treats memory as a short claim plus the words that support it, not as an invisible profile.

## Turn

One message you wrote in a session. Assistant replies, tool output, pasted blocks, injected context,
and PersonaKit's own extraction sessions are dropped before anything else happens.

## Memory

A short statement about you (one sentence, at most 300 characters) in one of seven categories:
`communication`, `work-style`, `tools`, `preferences`, `background`, `constraints`, `other`. For example "prefers direct, practical feedback"
(fictional). A memory without evidence cannot be stored. Its id is derived from its normalised text,
so the same claim found twice is one memory with more evidence.

## Evidence

The quote from your own turn that supports the memory, with the session it came from.

## States

![The four states of a memory: unconfirmed by default, then approved, restricted or archived by your decision](assets/memory-states.svg)

| State | Meaning | Served to assistants |
|---|---|---|
| `unconfirmed` | Proposed, not yet reviewed | Yes, labelled |
| `approved` | You confirmed it | Yes |
| `restricted` | You limited it | No (counted as withheld) |
| `archived` | You hid it | No |

Only you move a memory between states. Assistants can read and propose; a proposal always starts
as `unconfirmed`. The system never deletes a memory on its own.

## Retrieval

Reads use word overlap with the question. When fewer than three memories match, approved ones fill
the remaining places as standing context. This is a deliberately simple baseline, not a finished retriever:
matching is on whole words in Latin letters and digits, so questions and memories in other scripts are not matched in 0.1.