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

# Changelog

> New updates and improvements

***

<Update label="January 26, 2026" description="0.30.1">
  [Hyperspell Connect](/usage/connect) now supports a `providers` parameter to filter which integrations are shown. This lets you show only specific integrations to your users (e.g., `?providers=slack,notion`).
</Update>

<Update label="January 16, 2026" description="0.30.0">
  You can now add multiple memories in a single request using the new `/memories/add/bulk` endpoint.
</Update>

<Update label="December 11, 2025" description="0.28">
  You can now add [custom metadata](/usage/metadata) to your memories, and query them in your queries.
</Update>

<Update label="Sepember 29, 2025" description="0.24">
  The API now supports [evaluating](/usage/evaluation) queries and highlights.
</Update>

<Update label="August 6, 2025" description="0.23">
  You can now use [Webhooks](/usage/webhooks) to get notified when new memories are created.
</Update>

<Update label="August 6, 2025" description="0.22.1">
  You can now customize [Hyperspell Connect](/usage/connect) page to match your app's branding.

  The [Web Crawler](/integrations/all/web_crawler) now lets you specify the maximum depth and number of pages to crawl when you index a website.
</Update>

<Update label="August 6, 2025" description="0.22.0">
  The new `/auth/delete` endpoint deletes all user data, including all memories and stored connections. This can't be undone.
</Update>

<Update label="August 4, 2025" description="0.21.0">
  Improved file upload handling and made sure that memories created from files also have a `title` attribute. The `/memories/list` endpoint now also returns the title of each memory.
</Update>

<Update label="August 1, 2025" description="0.20.0">
  Added an new endpoint to delete specific memories. Also lets you weight data sources in your queries, so you can influence which documents are used to answer a query.
</Update>

<Update label="July 18, 2025" description="0.19.0">
  Consolidated our offerings and API endpoints. The old endpoints under `/documents` are now under `/memories`.

  Additionally, you can now choose which model to use to answer queries — we default to Llama 3.1 8B for speed and efficiency, but more complex queries can benefit from a different model
</Update>

<Update label="July 10, 2025" description="0.18.2">
  Added a native integration with [AgentStack](https://agentstack.sh)
</Update>

<Update label="June 26, 2025" description="0.18.1">
  The [MCP server](/advanced/mcp-overview) got an upgrade! You can now use it to query your data from any MCP client. You can now run it directly with `npx` or via a client like [Claude Desktop](https://www.anthropic.com/products/claude-desktop).
</Update>

<Update label="June 19, 2025" description="0.18.0">
  You can now use the `X-As-User` header to query data as a specific user while using an API key as your authentication. This saves a round trip to the server to generate a user token.
</Update>

<Update label="June 11, 2025" description="0.17.2">
  We rolled out our new infrastructure that dramatically reduces the latency of our query endpoint.

  Most queries against indexed data should now be less than 250ms (plus extra time if you request an answer).
</Update>

<Update label="Feb 27, 2025" description="0.6.0">
  We heard that our web app was a bit slow, so we dramatically improved the performance.

  We also improved handling of spreadsheets and PDFS.
</Update>

<Update label="Feb 24, 2025" description="0.5.5">
  No more waitlist! You can now sign up and start using Hyperspell.
</Update>

<Update label="Feb 3, 2025" description="0.5.3">
  Our [Python](https://pypi.org/project/hyperspell/) and [TypeScript](https://www.npmjs.com/package/hyperspell) SDKs are now available and you can use them in your project. The installation is as easy as:

  <CodeGroup>
    ```sh Python theme={null}
    # Or use poetry, uv, ...
    pip install hyperspell
    ```

    ```sh TypeScript theme={null}
    # Or use yarn, pnpm, ...
    npm install @hyperspell/hyperspell
    ```
  </CodeGroup>

  The SDKs are fully typed and come with a comprehensive documentation:

  <CodeGroup>
    ```python Python theme={null}
    from hyperspell import Hyperspell

    client = Hyperspell(api_key="YOUR_APP_TOKEN")
    ```

    ```typescript TypeScript theme={null}
    import Hyperspell from 'hyperspell';

    const client = new Hyperspell({ apiKey: 'YOUR_APP_TOKEN' });
    ```
  </CodeGroup>
</Update>