ai_test

ImDaeseong/ai_test (Python)

A new way for AI to search for data

View on GitHub

2GitHub stars

JavaScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 9a747c6d3f (2026-10-09).

Selected work

ImDaeseong
@ImDaeseong

“Harden imagevideo release evidence”. 11 files, 325 lines in imagevideo, the project root.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-22. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

Example questions

Where does ai_test handle “Harden imagevideo release evidence”?
What does imagevideo do in ai_test?

The prompt

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

Search the GitHub repository ImDaeseong/ai_test with XERJ (https://hub.xerj.org/corpus/imdaeseong--ai-test).
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/ImDaeseong/ai_test ai_test && git -C ai_test checkout 9a747c6d3f194adf1b5819c1d13a15b46447c6c0
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./ai_test --url http://127.0.0.1:9200 --prefix ai-test --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.

ImDaeseong API design and specification corpora

Selected work and consent: the XERJ registry.