yt-agent

yt-agent — summarize / highlights / Q&A / presentation / digest / review

One entry point for turning YouTube into artifacts. All data access goes through the uvx yt-mem-ai <cmd> CLI (see [[yt]] for the full command surface) — never touch the LanceDB store directly. Always invoke it exactly that way: zero-install and cached, so nothing has to be on PATH. Do not go looking for a yt-ai binary — the native plugins install no package. (Only inside a source checkout may you use uv run yt-ai <cmd>.) Single-quote every URL — YouTube URLs contain ?/&, which the shell globs on, so a bare URL fails: uvx yt-mem-ai fetch 'https://www.youtube.com/watch?v=ID' --captions-only. Everything is grounded in the transcript; highlight timestamps come from uvx yt-mem-ai search, never invented. The analysis is done by this agent — no API key, no OpenRouter.

Pick the scenario

• A — one video (a URL, a bare 11-char video_id, or "this video" as a follow-up): produce a summarize / highlights / qa / presentation artifact.
• B — process latest subscriptions ("catch up", "daily", "new uploads"): discover + fetch + analyze each + write a dated digest.
• C — subscriptions review ("review my subs", "themes lately", "what's been happening"): one cross-video synthesis over a date range.
• D — group (arbitrary set) ("process/review these videos <ids/urls>", "review channel ''", "review from to "): ingest a user-specified set, then per-video analysis + a group synthesis.

Core: analyze one video (used by A and B)

Given a video_id (and a URL if it may not be ingested yet):

1. Ensure ingested (idempotent): uvx yt-mem-ai show <video_id> --json.
   • not found and you have a URL → uvx yt-mem-ai fetch '<url>' --captions-only. If that prints no captions available: ..., fall back to uvx yt-mem-ai fetch '<url>' --whisper (downloads audio + transcribes — slower, always yields a transcript).
   • Blocked instead? Sign in to confirm you're not a bot → run uvx yt-mem-ai config set YT_COOKIES_BROWSER chrome and retry; captions blocked ... IP rate-limited → cookies won't help, see [[yt]]'s When YouTube blocks a fetch.
   • Already ingested → instant, no download (is_seen skips it).
2. Reuse if present: if the show --json output has a non-null summary, reuse it — skip generation unless the user asked for a fresh artifact.
3. Anchor highlights: for each candidate highlight phrase, run uvx yt-mem-ai search "<phrase>" --vector -k 3 and use the MM:SS from a returned line whose video_id matches. Never invent timestamps.
4. Produce (you, the model — no API): summary_md (2–4 sentence exec summary
   • key bullets), highlights JSON [{"start_s": <seconds>, "label": "..."}] (3–8, seconds from step 3), qa JSON [{"q": "...", "a": "..."}] (3–6).
5. Persist: uvx yt-mem-ai save-summary <video_id> "<summary_md>" --highlights '<json>' --qa '<json>'.