Mediarium

Self-hosted media manager for movies, TV, music, ebooks and audiobooks: search, download and organise, all in one Docker container

A new way for AI to search for data
View on GitHub
314GitHub stars

Go, TypeScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit f371ea332d (2026-11-02).

Selected work

memnos
@memnos

“use a saved Hardcover token for book search covers”. 21 files, 1,594 lines in internal/api, internal/books, web.

Licence

The repository

AGPL-3.0

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

Approach only

The author agreed by email on 2026-11-02. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: approach only

dockergolanghomelabmedia-managerradarr-alternativereactself-hostedsonarr-alternative

Example questions

The prompt

Paste it into your AI agent. It clones rdborg/Mediarium at the pinned commit and indexes it on your machine.

Search the GitHub repository rdborg/Mediarium with XERJ (https://hub.xerj.org/corpus/rdborg--mediarium).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/rdborg/Mediarium Mediarium && git -C Mediarium checkout f371ea332dc23952604e03b7e58a16a158e8ef9e
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./Mediarium --url http://127.0.0.1:9200 --prefix mediarium --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: AGPL-3.0. Read it for the approach only, do not copy code.

Related

Selected work and consent: the XERJ registry.