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

# Changelog

> New features, endpoints, and changes to the Video Datalake API.

<Update label="2026-08-03" description="Video Datalake — preview" tags={["Video Datalake"]}>
  ## Video Datalake

  First preview of the video data lake — **41 endpoints**:

  * **Collections** with fixed embedding (OmniRetriever), optional safety detection and face recognition.
  * **Ingestion** — upload by URL, file, or resumable session; attach live streams.
  * **Async operations** — uniform `202 + Operation` model with polling and HMAC-signed webhooks.
  * **Moments & derived content** — captions, transcripts, frames, clips, titles, summaries, speakers, entities.
  * **Search** — semantic, keyword, hybrid, and image, returning moment lists.
  * **Face library** and **safety-detection events**.

  Embeddings standardized on **OmniRetriever** (3072-dim, multilingual); captions & summaries by **OmniCaptioner**.
</Update>

<Update label="2026-08-03" description="Agents & tools" tags={["MCP", "CLI", "Plugin"]}>
  ## Agents & tools

  Operate the Datalake without writing glue code:

  * **[MCP Server](/mcp-server)** — connect Claude, Cursor, or any [MCP](https://modelcontextprotocol.io) client and drive the lake in natural language.
  * **[CLI](/cli)** and a **[Claude Code / Codex plugin](/plugin)** for terminal and agent workflows.
</Update>