OpenGithubs / OpenGithubs/weekly

【开源自荐】Mediary Scout:让 LLM agent 把你想看的影视转存进自己的网盘(115/夸克/光鸭)并回读验证

Open
#127 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
No language data
Stars
1.7k
Forks
71
PR merge metrics
No merged PRs in 30d

Description

你说要看哪部电影 / 剧 / 番,一个 LLM agent 跨资源站把最合适的资源转存进你自己的 115 / 夸克 / 光鸭网盘(秒传 / 离线,不下载到本地),转存后回读网盘验证到底落了什么,并持续追踪还缺哪几集。

Mediary Scout 演示:搜索 → agent 获取 → 转存 → 验证 → 入库

解决什么

大多数「媒体自动化」要么搜得好但不知道你到底缺哪集,要么会搬文件却从不验证落了什么。Mediary Scout 把「获取」当成一个状态问题,由一个凭证据而非凭感觉行动的 agent 驱动——按画质、中文字幕、去重挑片,转存后回读核对真实落地文件,没合格的宁可报「未找到」也不塞垃圾。季级状态机记着每部剧每季缺哪几集,定时巡检只回来补缺。

特点

  • 桌面版 Mac / Windows 双击即用,也能 docker compose up -d 挂 NAS / 软路由 24h 追更
  • 多盘 / 多账号:一个实例全家合用,各绑各的盘、各看各的库
  • 全程可观测:活动页实时队列 + agent 每步动作 ticker,转存失败如实报原因
  • 纯自部署、开源(AGPL),凭证只存你自己实例,作者看不到你任何东西

技术栈

Next.js(App Router / PPR)+ 进程内 worker 驱动的沙盒 agent + Postgres + Vercel AI SDK(任意 OpenAI 兼容端点)+ Electron 桌面壳。

工程上有个值得一提的点:给一个能真删你文件的 LLM agent 上确定性镣铐(预算闸门 / 回读验证 / 窄权限沙盒),写了篇复盘:

给 LLM agent 上镣铐 · 三个 bug 的复盘

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file, test, or entry point in OpenGithubs/weekly is mentioned. There is no requested repository change or completion condition to verify; the issue is a project showcase rather than an actionable contribution.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker-compose, electron, nextjs, postgres
Domain
content
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.