mcpField
V
video-memory

video-memory

github.com/oxbshwProductivity533536 installsUpdated 7w ago
Repository

About video-memory

video-memory is a persistent library of videos analyzed with watch-skill, retaining frames, OCR, transcripts, and past answers. It helps people find evidence in individual recordings or ask questions across videos, with results tied to video timestamps.

Key features

  1. 01Persistent index of analyzed videos
  2. 02Hybrid keyword and semantic search
  3. 03Search across multiple languages
  4. 04Video questions with timestamped evidence
  5. 05Cross-video synthesis with citations
  6. 06Batch indexing of playlists or folders

Use cases

  1. 01Find which recording showed a particular detail
  2. 02Retrieve evidence from a video by timestamp
  3. 03Compare decisions across meeting recordings
  4. 04Make a playlist searchable in one batch

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/oxbshw/watch-skill --skill video-memory

After installing, type/video-memoryin Claude Code to confirm it loaded.

Details

From the project README

Video memory

Every video ever watched on this machine is still here — frames, OCR, transcripts, and past answers, in one persistent index under ~/.watch-skill/. You never have to say "I don't remember that video." Sessions don't expire it; watching more videos makes it more useful.

What's in the library?

watch-skill list

Every indexed video: id, title, duration, when it was analyzed. Check here before watching anything — it may already be in memory from a previous session.

Find something across all of it

watch-skill search "<phrase or keywords>"

Hybrid keyword + semantic search across every video, any language (Arabic folding, CJK and Thai segmentation are handled). Hits come back with video + timestamp; follow up on a hit with:

watch-skill ask <video_id> "<the user's actual question>"
watch-skill ask <video_id> "what is on screen at <timestamp>?"

Questions that span videos

"What did we decide about the pricing page across those meetings?" — questions no single video answers go to the library synthesizer:

watch-skill library ask "<the question>"

It answers from distilled notes across every indexed video, drills into real evidence, and cites video + timestamp for each finding. When it says the library does not clearly answer, trust that — do not stitch a guess together from weak search hits. watch-skill library overview shows what the library knows (videos, note counts, entities recurring across videos).

For "which video showed X" (locate, not synthesize), plain search is the right tool; then ask the hit video.

Batches build memory fast

A playlist or a folder of recordings goes in as one call — watch-skill batch "<playlist-or-folder>" — and the whole set becomes searchable memory (see watching-videos).

Comments

Markdown supported