> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omi.me/llms.txt
> Use this file to discover all available pages before exploring further.

# Conversations & memories

> The data model behind an Omi account: conversations, what gets extracted from them, and memories.

Omi keeps two kinds of records. **Conversations** hold everything about one stretch of talk. **Memories** are short facts about you, extracted from conversations and linked back to them.

## Processing a conversation

When a conversation ends, the backend:

1. Generates a title, an overview, and a category from the transcript.
2. Extracts action items and calendar events.
3. Extracts memories worth keeping about you.
4. Indexes the conversation for search and runs any apps you installed that act on finished conversations.

Conversations that turn out to have no useful content are marked `discarded` rather than deleted.

## Conversations

| Field | Meaning |
| - | - |
| `started_at`, `finished_at` | When the conversation happened |
| `source` | Where it was captured (wearable, phone, desktop, and so on) |
| `transcript_segments` | The transcript ([segment fields](https://docs.omi.me/doc/how-omi-works/capture-and-transcription.md#transcript-segments)) |
| `structured` | Title, overview, category, action items, and events |
| `apps_results` | Output from apps that processed it |
| `photos`, `audio_files`, `geolocation` | Attachments, when captured |
| `visibility` | `private`, `shared`, or `public` |

Uploads that arrive out of order are merged by capture time, so a conversation recorded offline lands where it belongs. Very long recordings are split at segment boundaries into several conversations, each with its own summary.

## Memories

A memory is one short fact, such as a preference, a habit, or something you mentioned. Each memory records the conversation it came from, so you can always trace it back.

| Category | Meaning |
| - | - |
| `interesting` | Notable facts: opinions, hobbies, stories |
| `system` | Patterns and preferences: work habits, routines |
| `manual` | Facts you added yourself |

Extraction is deliberately selective: it skips mundane details and near-duplicates. You can review, edit, and delete memories in the app.

## Reading this data

Conversations, memories, action items, and goals are available through the [Developer API](https://docs.omi.me/doc/developer/api/overview.md), the [MCP server](https://docs.omi.me/doc/developer/mcp/introduction.md), and the [CLI](https://docs.omi.me/doc/developer/cli/introduction.md), all scoped to your account.

> [!NOTE]
>
> Storage layout, encryption levels, and indexing internals live next to the code in [`backend/docs/storing-conversations.md`](https://github.com/BasedHardware/omi/blob/main/backend/docs/storing-conversations.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.