peepshow/ sinks/ sqlite

Reel #01 Local SQL archive

peepshow sink / sqlite

SQLiteA local video archive that sqlite3 can query.

One file, zero server, full SQL. Ships with auto-schema and upsert.

drop · process · sqlite

What it does

Archive every peepshow run — video metadata, all extracted frames, timings, and scene scores — into a single SQLite file on disk. Queryable with any SQLite tool, portable, zero-config.

When to reach for it

  • Keep a searchable log of every video an LLM has seen
  • Join run history with your own sqlite tables for domain-specific indexing
  • Ship a prebuilt `.sqlite` with a video dataset so agents can grep metadata before watching frames

Install

# runtime + optional driver (native module, needs toolchain)
npm i -g peepshow
npm i -g better-sqlite3

Use it

peepshow ./keynote.mp4 --sink sqlite \
  --sink-arg path=~/peepshow.sqlite

Make it automatic

Register the sink once — every run fires it afterward. Scope by --when so it only runs for matching videos.

peepshow sinks add sqlite
peepshow sinks add sqlite --when extension=mp4,mov
peepshow sinks add sqlite --when path=/Volumes/Work/

Configuration

  • PEEPSHOW_SQLITE_PATH Override the default database location.

Use with an LLM agent

Every peepshow sink reads its config from env vars and receives a single JSON payload on stdin. An LLM agent (Claude Code, Cursor, Windsurf, Gemini, Codex) can drive the SQLite sink automatically when three things are true:

  • the env vars below are exported in the agent's shell (or a project .env it can load),
  • the peepshow CLI is on PATH — install with npm i -g peepshow,
  • a peepshow auto-sink is registered for the run (optional but recommended — makes invocation zero-argument).

1. Set the environment

This sink has no required env vars — it writes to a local path. Pass the destination via --sink-arg:

peepshow ./keynote.mp4 --sink sqlite \
  --sink-arg path=~/peepshow.sqlite

2. Register as an auto-sink

peepshow sinks add sqlite
peepshow sinks add sqlite --when extension=mp4,mov

3. Example LLM session

You → drop a .mov into Claude Code.

Claude → auto-invokes /peepshow:slides ./clip.mov. peepshow extracts frames + audio, the SQLite sink forwards the run to the configured database. Claude replies with a summary and a link to the created record.

The transcript rides along in the payload whenever the audio pass transcribes successfully.

Write your own

A sink is any executable that reads the --emit json payload on stdin. Shell, Node, Python, Go — the spec's in docs/PLUGINS.md. Register persistent ones with peepshow sinks add-cmd 'your-command'.