subzero

Subtitle cleanup, timing verification, Apple Vision caption recovery, and local translation with a Jellyfin worker

A new way for AI to search for data
View on GitHub
1GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit de6896de03 (2026-10-29).

Selected work

Yuri Barreira
@yuri-rod

“Add queued API inference, semantic repair, and resource-aware benchmarks”. 26 files, 2,152 lines in tests, src/subzero.

Licence

The repository

MIT

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

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-31. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

cliffmpegjellyfinmediapythonsdhsrtsubtitle-tools

Example questions

The prompt

Paste it into your AI agent. It clones yuri-rod/subzero at the pinned commit and indexes it on your machine.

Search the GitHub repository yuri-rod/subzero with XERJ (https://hub.xerj.org/corpus/yuri-rod--subzero).
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/yuri-rod/subzero subzero && git -C subzero checkout de6896de0364227af0640a74ef34a0156041a266
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./subzero --url http://127.0.0.1:9200 --prefix subzero --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: MIT. Keep the copyright notice and credit the authors.

Related

Selected work and consent: the XERJ registry.