niche-finder

A self-hosted YouTube research tool — your own NexLev / vidIQ / ViewStats, running on the free YouTube Data API and a local PostgreSQL.

Find niches, viral videos from small channels, outlier channels, trending categories and keywords over any period (24 hours to 90 days and beyond); track channels and watch their growth; check a title, hook or idea against what actually worked in a niche — and get the same numbers in three places:

• Claude Desktop (or any MCP client) — 100 tools and 7 ready-made scenarios;
• a web dashboard on localhost:8080;
• a Chrome extension that puts the metrics on top of YouTube itself.

No subscription and no paid LLM key: semantic judgement ("is this channel faceless?", "is this on topic?") is done by the model calling the tools, not by the server. An LLM is optional and off by default.

Contents

• Why niche-finder
• Features
• Screens
• Quick start
• How it works
• Documentation
• Repository layout
• Privacy and security
• Contributing
• License

Why niche-finder

• Yours, end to end. Your key, your database, your machine. No telemetry; by default the app talks to exactly two hosts — www.googleapis.com and www.youtube.com (RSS feeds).
• History the API doesn't give you. The YouTube API only ever says "how many views right now". A background worker writes the numbers down on a schedule, so views per hour, acceleration, subscriber growth and title or thumbnail swaps actually exist.
• Honest numbers. RPM and revenue come as a range, not one invented figure; every signal carries its sample size; below a minimum sample you get "not enough data" instead of a guess; there is no single opaque "SEO score".
• Quota-aware. Reading is cheap, searching is scarce. Every collector reports what it spent, uploads are walked through playlists (1 unit per 50 videos), and new uploads are spotted through free RSS feeds.
• One codebase, three doors. The MCP server, the HTTP API and the worker call the same use cases, so Claude and the dashboard can never disagree.

Features

Find a niche

• Viral videos from small channels and outlier channels (a video against its own channel's median), over any period, with subscriber, length, Shorts, RPM and YouTube Partner Program threshold filters.
• Trending categories and keywords with lift and momentum; best time to publish; title phrases that correlate with breakouts.
• Niche trend — growing / stable / cooling / saturated — from the last 30 days against the 90 before: supply, demand (views projected to day 30), new channels and whether newcomers break out.
• A niche map (k-means over channel embeddings) and semantic similarity of channels and videos via pgvector.
• Idea checker: is a topic free, recently covered, proven or a flop in this niche?
• Content calendar: drafts on a week or month grid, drag one onto a day, the niche's best hours as a hint, a Telegram/digest reminder the day before and when it is due.
• Collaboration partners: similar channels of your size (×0.5–×2 subscribers), active in the last 30 days and not templated, each with the numbers that picked it, one click to the tracker.
• Net profit: revenue range minus your cost profiles (per video, per minute of video, monthly overhead) for a channel's month, a video or a niche's typical video, with break-even views; your real RPM on a connected channel.
• What outliers share: for a niche, what its outliers have in common against ordinary videos -- number or "?" in the title, video and title length, tags, weekday and time -- by the numbers, no LLM, Shorts and long-form apart.
• Where to enter: every niche scored 0–100 from six visible terms (demand trend, supply growth, newcomers breaking out, RPM, templated channels, policy signals), sortable by any column, with a side-by-side comparison of 2–3 niches.
• Language gaps: outliers in one language and whether anything like them exists in another (not made / made weakly / already a hit), from the videos you collected.
• Export a niche's videos to TSV or CSV.

Study channels and videos

• Channel tracking: growth by window, views-per-hour of every upload, a revenue range, which YPP thresholds it visibly meets (and how it fares under the rules from 2027-02-01), the next subscriber milestones with an estimated date, and a "gone" mark when a channel disappears from YouTube.
• Repackaging: title and thumbnail swaps after publishing, before and after side by side, with views per hour around the swap.
• Template risk: how much a channel's (or a niche's) recent uploads look like one template repeated — the pattern behind "inauthentic content" demonetisations. A heuristic, not a verdict.
• Sponsor map: which brands pay creators in a niche, read from descriptions; promo codes and affiliate links kept apart.
• Similar thumbnails with local CLIP vectors: thumbnails that look like an outlier's, search by description ("red arrow, shocked face"), and a niche's thumbnail styles with how each performs. Opt-in.

Plan your own video

• Outlier to brief: one call turns a video that beat its channel into a working brief — hook, niche title patterns, whether the topic is already covered, title candidates and thumbnail references.
• Metadata review: a draft's title, description and tags checked against your corpus, signal by signal, with near-duplicate topics; drafts can be linked to the published video to see whether the review held up.
• Hook score: the first ~30 seconds of a transcript or your draft intro, rated 0–100 in English and Russian; compared with a niche's outliers.
• Content gaps: questions and requests from a niche's comments that no video answers yet, ranked by demand.
• Title scoring and suggestions, transcripts with hybrid (keyword + semantic) search, comment insights and "why did it take off" explanations (the last ones need the optional LLM).

Stay on top of it

• Alerts for your watchlist: a new outlier, view acceleration, a title change, a channel breaking its silence, a channel or video that vanished, a subscriber milestone passed, and a new video on a topic you named in plain words — on the dashboard, in the extension's badge, and to Telegram or a webhook (one by one or as a morning digest).
• A swipe file for videos and channels you want to come back to.
• Your own channels: connect them through Google OAuth (your own client, read-only) and see real YouTube Analytics numbers — views, retention, revenue, RPM — next to a niche, and your real RPM against niche-finder's estimate.

Optional extras

• An LLM via OpenRouter (free models rotate on their own) or a local Ollama for background labelling, comment insights, title generation and explanations — with a daily budget.
• Multi-user mode (experimental): invited accounts, each with their own watchlist, drafts, alerts and a share of the quota.

Screens

<table> <tr> <td width="50%"><img src="assets/viral.jpg" alt="Viral videos from small channels"><br>_{<b>Viral videos</b> — small channels that beat their expectations}</td> <td width="50%"><img src="assets/outliers.jpg" alt="Outlier channels"><br>_{<b>Outlier channels</b> — best video's multiplier against the channel's median}</td> </tr> <tr> <td width="50%"><img src="assets/channel.jpg" alt="Channel analytics"><br>_{<b>Channel</b> — growth, snapshots, revenue range, similar channels}</td> <td width="50%"><img src="assets/keywords.jpg" alt="Keywords"><br>_{<b>Keywords</b> — trendScore, lift, momentum}</td> </tr> <tr> <td width="50%"><img src="assets/categories.jpg" alt="Categories"><br>_{<b>Categories</b> — share and growth across YouTube niches}</td> <td width="50%"><img src="assets/tracker.jpg" alt="Channel tracker"><br>_{<b>Tracker</b> — collect and follow specific channels}</td> </tr> <tr> <td width="50%"><img src="assets/niches.jpg" alt="Niches"><br>_{<b>Niches</b> — everything collected under your own labels}</td> <td width="50%"><img src="assets/data.jpg" alt="Data"><br>_{<b>Data</b> — database state and manual collection}</td> </tr> <tr> <td width="50%"><img src="assets/find.jpg" alt="Find a niche"><br>_{<b>Find a niche</b> — semantic search over the collected corpus, no quota}</td> <td width="50%"><img src="assets/alerts.jpg" alt="Alerts"><br>_{<b>Alerts</b> — new outliers and accelerating videos on tracked channels}</td> </tr> <tr> <td width="50%"><img src="assets/packaging.jpg" alt="Repackaging history"><br>_{<b>Repackaging</b> — title and thumbnail changes, before / after}</td> <td width="50%"><img src="assets/ideas.jpg" alt="Idea checker"><br>_{<b>Idea checker</b> — free, recently covered, proven demand or flop}</td> </tr> <tr> <td width="50%"><img src="assets/compare.jpg" alt="Compare trajectories"><br>_{<b>Compare</b> — views by age for up to five videos, side by side}</td> <td width="50%"><img src="assets/policy.jpg" alt="Monetization-policy signals"><br>_{<b>Policy signals</b> — YouTube's three inauthentic-content categories, no risk percentage}</td> </tr> <tr> <td width="50%"><img src="assets/enter.jpg" alt="Where to enter"><br>_{<b>Where to enter</b> — every niche scored 0–100, each term visible, sortable}</td> <td width="50%"><img src="assets/language.jpg" alt="Language gaps"><br>_{<b>Another language</b> — outliers in English and whether Russian has anything like them}</td> </tr> </table>

The dashboard has 24 sections in the sidebar plus niche, channel and brief pages — alerts, idea checker, transcripts, niche map, title check, repackaging, metadata review, your own channels and more; frontend/README.md walks through each one.

Quick start

You need Docker and a free YouTube Data API v3 key (Google Cloud Console → enable