> AI agents: this is one page from PostHog's docs. Full index of Markdown docs for LLMs: https://posthog.com/llms.txt

# Linking Hyperspell as a source

**Alpha release**

This source is currently in **alpha**. The interface and available tables may change.

![](https://res.cloudinary.com/dmukukwp6/image/upload/texture_tan_9608fcca70)

![](https://res.cloudinary.com/dmukukwp6/image/upload/texture_tan_dark_a92b0e022d)

Let AI connect your sources for you

Skip the manual setup — run this in your project and the wizard auto-detects your databases and APIs and connects them to PostHog.

`npx @posthog/wizard warehouse`

![PostHog Wizard hedgehog](https://res.cloudinary.com/dmukukwp6/image/upload/wizard_3f8bb7a240.png)

![](https://res.cloudinary.com/dmukukwp6/image/upload/wizard_3f8bb7a240.png)Let AI connect your sources for you

The Hyperspell connector pulls your app's AI memory layer into the PostHog data warehouse: indexed memories, data-source connections, extracted entities, prior queries, and generated context documents.

## Prerequisites

You need a [Hyperspell](https://hyperspell.com/) account with an API key created in the [Hyperspell dashboard](https://app.hyperspell.com/). API keys are region-specific, so note whether your Hyperspell app lives in the US or EU region.

## Adding a data source

1.  In PostHog, go to the [Sources tab](https://app.posthog.com/data-management/sources) of the data pipeline section.
2.  Click **\+ New source** and click **Link** next to this source.
3.  Enter your credentials (see [Configuration](#configuration) below) and click **Next**.
4.  Select the tables you want to sync, choose a sync method and frequency, then click **Import**.

Once the syncs are complete, you can start querying this data in PostHog.

The source needs:

-   **API key**: created in the [Hyperspell dashboard](https://app.hyperspell.com/).
-   **Region**: the Hyperspell region your app lives in (US or EU). A key only works in the region it was created in.
-   **User IDs** (optional): memories, connections, vaults, and entities in Hyperspell are scoped to individual users of your app. To sync them, enter a comma-separated list of user IDs – each is fetched on Hyperspell's `X-As-User` header. Leaving this empty syncs app-level data only.

## Sync modes

Each table can be synced in one of several modes, depending on what the source supports:

-   **Webhook** (when available) – the source pushes changes to PostHog in real time. Fastest freshness, lowest ongoing cost, and the only mode that reliably captures updates and deletes.
-   **Incremental** – only new or updated rows are synced on each run, using a cursor field (such as an `updated_at` timestamp). Cheaper than a full refresh, but deletes aren't captured.
-   **Append only** – new rows are appended using a cursor field; existing rows are never updated. Ideal for immutable, append-only tables like event logs.
-   **Full refresh** – the whole table is reloaded on every sync. Use it when a table has no reliable cursor or when you need deletions reflected.

See [sync methods](/docs/cdp/sources.md#sync-methods) for a full explanation of how each mode works and how to choose between them.

Hyperspell's API doesn't expose server-side timestamp filters, so all tables sync as a full refresh.

## Configuration

| Option | Type | Required |
| --- | --- | --- |
| `API key` | password | Yes |
| `Region` | select | Yes |
| `User IDs (optional)` | text | No |

## Supported tables

| Table | Description | Sync method | Incremental field | Primary key |
| --- | --- | --- | --- | --- |
| `memories` | Documents indexed in Hyperspell's memory layer, ingested from connected sources (Slack, Notion, Gmail, Google Drive, and more) or added directly via the API. | Full refresh | — | user\_id, source, resource\_id |
| `connections` | Data-source connections users (or the app) have authorized, linking an integration like Slack or Google Drive to Hyperspell for indexing. | Full refresh | — | user\_id, id |
| `integrations` | The catalog of integrations available to the app, with each integration's auth provider and selection requirements. | Full refresh | — | id |
| `vaults` | Vault collections of manually added documents, with the number of documents in each. | Full refresh | — | user\_id, collection |
| `entities` | Entities (people, companies, projects, ...) extracted from indexed memories, with mention counts and attributes. | Full refresh | — | user\_id, id |
| `queries` | Prior queries issued against the app's memory index, useful for evaluating recall quality. | Full refresh | — | query\_id |
| `context_documents` | Context documents generated by Hyperspell for the app, summarizing indexed knowledge. | Full refresh | — | document\_id |
| `users` | The app's users: the distinct document owners in Hyperspell, with how many documents each owns. | Full refresh | — | user\_id |
| `integration_channels` | Channels and chats available on each connection whose integration supports channel selection (for example Slack or Microsoft Teams), with whether each one is selected for indexing. | Full refresh | — | user\_id, connection\_id, id |

## Troubleshooting

-   **"Invalid Hyperspell API key"** when connecting: the key is invalid, expired, or was created in a different region than the one selected. Check the region and generate a fresh key in the Hyperspell dashboard if needed.
-   **`memories` or `connections` tables are empty**: this data is per-user in Hyperspell. Add the user IDs you want to sync to the **User IDs** field of the source settings.

If your sync is failing or data looks wrong, see the [Data warehouse troubleshooting guide](/docs/data-warehouse/troubleshooting.md). If that doesn't help, [contact support](https://us.posthog.com/#panel=support%3Asupport%3Adata_warehouse%3A%3Atrue) – we're happy to help.

### Still have questions?

Ask PostHog AI

### Was this page useful?

HelpfulCould be better