Startup Ideas Bank
Media Library Automation for the 0.1%
AI roast score: 36/100 (F)
The idea
fancydirty/mediary-scout — Agent-driven media library for your cloud drives (115 / Quark / 光鸭 GuangYaPan).
An agent-driven media library for your cloud drives.
Quick start ·
Deploy guide ·
Live demo ↗ ·
中文文档
You ask for a movie, show, or anime; an LLM agent scouts resources across your indexers, transfers the best match into your own 115 / Quark / 光鸭 drive, verifies what landed, and keeps tracking what's still missing.
Above: the read-only live demo — search → 获取 → the agent works through search, transfer, and verification.
Disclaimer. Mediary Scout is open-source, self-hosted software . It is not offered, and never will be offered, as a hosted service — you run your own instance and bring your own drive / LLM / metadata credentials. It performs the same kinds of file operations you could do by hand in your own cloud drive. See docs/distribution-and-legal-positioning.md for the project's stance.
Contents
What it is
Features
Architecture
Quick start
Deploy
Demo
Supported drives
Status & limitations
Credits & upstream
What it is
Most "media automation" either searches well but doesn't know what you're actually missing, or moves files but never verifies what landed. Mediary Scout treats acquisition as a state problem , driven by an agent that acts from evidence, not vibes:
Multi-drive, brand-extensible — 115, Quark, and 光鸭 (GuangYaPan) today, each a first-class workspace (a tree model: one account, many drives). Adding a new drive brand is a contained plugin.
Agent-driven selection — the agent reads real search results and picks by quality preference, Chinese-subtitle needs, and de-duplication, then verifies the transfer after it happens.
Tracking & scheduled gap-fill — season-level state machine; a scheduled sweep comes back only for shows that still have missing episodes.
Cloud-native — it transfers shares/magnets straight into your drive (秒传 / save), it does not download to a local disk.
It's for advanced self-hosters comfortable with their own cloud-drive accounts and credentials — not a one-click consumer product.
Features
Search → acquire — find a title, hit 获取, the agent takes over
Library wall — what you have, per drive, with missing / airing badges
Show detail — season coverage, gaps, tracking state
Realtime activity — a live queue + agent action ticker while it works
Notifications — per-acquisition + daily digest, multi-channel push
Settings — drives, quality, language, LLM (BYO-key), Prowlarr, PanSou
Multiple drives appear as a workspace switcher with per-brand icons:
Architecture
A web app enqueues work; a long-running worker drives a sandboxed agent that has narrow, audited powers while the deterministic workflow owns
The roast
You're targeting a minuscule segment of advanced self-hosters who are comfortable with setting up and managing their cloud drives. This is a tiny, niche market that offers little to no growth potential. Your moat is 'speed', but there's no evidence that speed alone can attract and retain such a limited audience. The fact that it's open-source and self-hosted also means you have no recurring revenue model, making it financially unsustainable. Additionally, you admit it's not a one-click consumer product, which further narrows your already small audience. This isn't a business; it's a hobby project with delusions of grandeur.
Red flags
- Niche market
- No recurring revenue model
- Complex setup
Verdict
Your idea is a niche hobby project with minimal market potential and no clear path to revenue.
Roast your own startup idea →