Ross ROSS = Recommend OSS · open-source software intelligence for agents

fancydirty/mediary-scout

Agent-driven media library for your cloud drives (Quark 夸克 / 115 / 光鸭 GuangYa / 123网盘 / 天翼 Tianyi) observed · 2026-08-28

github.com/fancydirty/mediary-scout · homepage · TypeScript · 0BSD (permissive) observed · 2026-08-28

Health v2 · maintenance only

79/100

  • Activity 99
  • Release rhythm 96
  • Longevity 5

Flags: young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 2
  • age_days: 74
  • days_rel: 27
  • days_push: 7
  • n_releases_24m: 12

Full methodology

Adoption not part of the score

1356 stars · 88 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Mediary Scout is an agent-driven media library application that searches for movies, shows, and anime across indexers using an LLM agent, then transfers the best match directly into Chinese cloud drives (Quark, 115, GuangYa, 123, Tianyi) without touching local disk. It verifies transferred files by reading them back, tracks missing episodes with a season-level state machine, and offers a signed macOS/Windows desktop app or Docker self-hosted deployment.

Use cases

  • automatically download movies and shows to my quark or 115 cloud drive
  • agent that searches and transfers media into chinese netdisk
  • track missing episodes of a tv series and auto-fetch new ones
  • build a media library on top of my cloud drive without a local server
  • find best quality release with chinese subtitles across indexers
  • self-hosted media automation for nas with docker
  • verify transferred files are complete after offline download

When to choose

  • you use Chinese cloud drives (Quark, 115, GuangYa, 123, Tianyi) and want hands-off media acquisition
  • you want an LLM agent to handle search, selection, transfer, and verification end-to-end
  • you prefer a no-Docker desktop app with bundled SQLite over a *arr stack
  • you need multi-account isolation for family members on one instance

When to avoid

  • you need torrenting or local storage rather than cloud-drive transfers
  • you rely on Western cloud providers or direct downloads unsupported by its drive plugins
  • you want a fully deterministic pipeline without depending on an LLM API key
  • you need a mature, long-proven project — it is young and rapidly evolving

Facets

application · maturity active

agent-framework search-engine file-upload chat-interface self-hosted media self-hosted windows self-hosted cross-platform cloud-drive media-library llm-agent chinese-cloud-drives quark 115 tianyi tmdb tv-tracking transfer-verification ai-agents automation macos electron docker

2 sources

Member repositories

RepositoryRoleHealth v2
fancydirty/mediary-scoutmain79

For agents

markdown · JSON · MCP: product_card(name="fancydirty/mediary-scout")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem