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

# Memory Categories

> 13 auto-tagged categories for extracted memories

When Cognis extracts facts from conversation messages, each memory is automatically assigned a category. This enables filtered retrieval and helps organize what the agent knows about a user.

## Default Categories

| Category        | Description                                              | Example                                       |
| --------------- | -------------------------------------------------------- | --------------------------------------------- |
| `identity`      | Personal identity, name, demographics, age, location     | "Alice is 28 years old"                       |
| `relationships` | Family, friends, social connections, pets                | "Alice has a dog named Max"                   |
| `work_career`   | Job, profession, workplace, colleagues, business         | "Alice works at Google as a data scientist"   |
| `learning`      | Education, skills, knowledge, certifications, languages  | "Alice speaks French and Python"              |
| `wellness`      | Health, fitness, medical conditions, diet, exercise      | "Alice runs 5K every morning"                 |
| `lifestyle`     | Daily habits, routines, sleep, transportation            | "Alice commutes by bike"                      |
| `interests`     | Hobbies, passions, entertainment, sports, games          | "Alice loves hiking and Taylor Swift"         |
| `preferences`   | Likes, dislikes, choices, favorites, style               | "Alice prefers dark mode"                     |
| `plans_goals`   | Future plans, aspirations, goals, dreams, intentions     | "Alice plans to visit Japan next year"        |
| `experiences`   | Past events, travel, memories, experiences               | "Alice went to Bali last summer"              |
| `opinions`      | Views, beliefs, attitudes, philosophical                 | "Alice thinks remote work is more productive" |
| `context`       | Session-specific context, current tasks, immediate needs | "Alice is debugging a FastAPI endpoint"       |
| `misc`          | Anything that doesn't fit other categories               | General facts                                 |

## Accessing Categories

Categories are stored in the memory's metadata:

```python theme={null}
resp = m.get_all()
for mem in resp["memories"]:
    print(f"[{mem['metadata']['category']}] {mem['content']}")

# [identity] Alice's name is Alice
# [work_career] Alice works at Google as a data scientist
# [interests] Alice loves hiking
```

## Custom Categories

Override the defaults by passing a custom dictionary to `CognisConfig`:

```python theme={null}
from cognis import Cognis, CognisConfig

config = CognisConfig(
    categories={
        "product_feedback": "User feedback about products and features",
        "support_issues": "Technical issues and bug reports",
        "account_info": "Account details, subscription, billing",
        "preferences": "User preferences and settings",
        "misc": "Anything else",
    }
)

m = Cognis(config=config, owner_id="user_1")
```

The LLM extraction prompt adapts to use your custom categories for classification.

## How Categorization Works

During `add()`, the LLM extraction step:

1. Reads the conversation messages
2. Extracts discrete facts as individual memory records
3. Assigns each fact to the most appropriate category from the configured list
4. Checks for duplicates against existing memories (threshold: 0.85 similarity)
5. Stores new facts or updates existing ones with versioning