> ## Documentation Index
> Fetch the complete documentation index at: https://metacognition-fdc534de-master.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Migrate from Supermemory

> Map Supermemory calls to Tex calls.

The Tex Python SDK keeps Supermemory-compatible calls for the verbs both SDKs support. If you use `supermemory.add(...)`, `client.search(...)`, or `client.profile(...)`, most of the migration is installing `tex-sdk` and changing the base URL.

## Drop-in compatibility

These calls work the same in Tex:

| Supermemory                              | Tex                                                               |
| ---------------------------------------- | ----------------------------------------------------------------- |
| `client.add(content, container_tag=...)` | `tex.add(content, container_tag=...)`                             |
| `client.search(q, ...)`                  | `tex.search.documents(q, ...)` (or `tex.search.memories(q, ...)`) |
| `client.profile(container_tag, ...)`     | `tex.profile(container_tag, ...)`                                 |
| `client.documents.list()`                | `tex.documents.list()`                                            |
| `client.documents.get(id)`               | `tex.documents.get(id)`                                           |
| `client.documents.update(id, ...)`       | `tex.documents.update(id, ...)`                                   |
| `client.documents.delete(id)`            | `tex.documents.delete(id)`                                        |
| `client.documents.batch_add([...])`      | `tex.documents.batch_add([...])`                                  |

<Note>
  Tex's `search` is a **resource**, not a callable. `tex.search(q)` raises `TypeError`. Use `tex.search.documents(q)` or `tex.search.memories(q)`. `tex.search.execute(q)` is also available as an alias for `tex.search.documents(q)`.
</Note>

Tex's `/v3/*` and `/v4/*` paths accept the raw API key as Bearer for Supermemory compatibility. The SDK routes those calls automatically.

## Exclusive Tex features

These Tex-only verbs can be adopted one at a time:

| Verb                              | What it adds                                                         |
| --------------------------------- | -------------------------------------------------------------------- |
| `tex.conversations.remember(...)` | Native conversation-turn ingestion with role/timestamp/observations. |
| `tex.recall(...)`                 | Confidence-scored retrieval with active/deep modes.                  |
| `tex.usage.today()`               | Read your token totals without leaving Python.                       |

## Migration steps

<Steps>
  <Step title="Install Tex">
    ```bash theme={null}
    pip uninstall supermemory
    pip install tex-sdk
    ```
  </Step>

  <Step title="Swap the import">
    ```python theme={null}
    # before
    from supermemory import Supermemory
    client = Supermemory(api_key=...)

    # after
    from tex import Tex
    client = Tex(api_key=..., base_url="https://api.getmetacognition.com")
    ```
  </Step>

  <Step title="Run">
    Existing `add` / `search` / `profile` calls keep working unchanged.
  </Step>

  <Step title="Adopt Tex-native verbs (optional)">
    Replace your conversation-history pattern with `tex.conversations.remember` + `tex.recall` for stronger temporal awareness and confidence scoring. The mental model is in [How memory works](/concepts/memory-model).
  </Step>
</Steps>

## Behavioral differences

* **Auth.** Supermemory uses the API key as Bearer. Tex does the same on `/v3/*` and `/v4/*`, but exchanges to JWT for Tex-native paths. The SDK handles both.
* **Retention.** Memory is persistent. Tex does not wipe free-tier memory on a timer. It stays until you delete it.
* **Pricing.** Tex bills on `tokens_in` / `tokens_out`, not document count. For document-heavy workloads, measure with `tex.usage.summary()` after a representative day.
* **Profiles.** Tex's `profile` aggregates over `container_tag` like Supermemory's. Backfill works without changes.

If you hit a Supermemory verb that doesn't behave identically, file an issue.