Use case · Media search

Search everything you've watched and listened to

Save once. Query anywhere. BrainTube auto-captures your videos, podcasts, articles and PDFs into a knowledge base every AI can read — so the thing you half-remember hearing six months ago is one query away.

The pain: saves that rot

You bookmarked the video. You queued the podcast. You saved the article. None of it is searchable by what was actually said. Playlists are graveyards. The one quote you need is buried in a 90-minute interview you can't skim.

What BrainTube does

  • Auto-captures from YouTube with segmented transcripts.
  • Transcribes podcasts and any audio you save.
  • Ingests PDFs, EPUBs, web articles, Notion (4-hour sync), meeting audio, and screenshots.
  • Builds per-item semantic embeddings and pulls out entities.
  • Links everything in a Postgres knowledge graph with PageRank-style retrieval.

The result: you can ask "that thing the founder said about pricing leverage" and land on the exact segment — across every source you've ever saved.

Query it from any AI

BrainTube exposes your library through a live MCP server (in the official MCP registry and on Smithery). Claude, ChatGPT, Cursor — and any future MCP-capable model — read straight from your corpus. No copy-paste, no re-explaining. Here's how the MCP memory layer works.

Why nothing else does this

Note apps make you type. Bookmark apps store URLs, not meaning. BrainTube is the only memory layer where the index fills itself from media — and is queryable from every AI you'll use, not just one.

Frequently asked

Can I search my YouTube 'watch later'?
Yes. BrainTube ingests videos you save and produces segmented transcripts with semantic embeddings, so you can search by what was actually said — not just by title.
Does it transcribe podcasts?
Yes. Podcasts and any audio you save are transcribed and embedded the same way as video, then queryable alongside everything else in your library.
Can I search PDFs and articles too?
Yes. PDFs, EPUBs, and web articles are first-class. So are screenshots, Notion pages (4-hour sync), and meeting audio. One library, every format.
How do I query my saves from ChatGPT or Claude?
BrainTube ships an MCP server. Claude.ai connects in one click via OAuth; Cursor, Claude Desktop, and other clients use a small JSON config. See the connect page for setup.

Save once. Query anywhere.

For every AI you'll use.

Start free

Keep reading