acforvs /

archdb

A collection of open sourced pretraining recipes

A new way for AI to search for data

View on GitHub

6GitHub stars

TypeScript, Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 1c9a690857 (2026-10-22).

Selected work

Vlad
@acforvs

“Make model specs and sources easier to browse”. 92 files, 3,688 lines in web, exports, data.

Licence

The repository

MIT

From GitHub's licence detection. A person still checks the LICENSE file at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-23. 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 archdb handle “Make model specs and sources easier to browse”?
What does web do in archdb?

The prompt

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

Search the GitHub repository acforvs/archdb with XERJ (https://hub.xerj.org/corpus/acforvs--archdb).
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/acforvs/archdb archdb && git -C archdb checkout 1c9a6908571f690a942c0e1333cf4bc47c658b9c
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./archdb --url http://127.0.0.1:9200 --prefix archdb --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.

Vlad API design and specification corpora

Selected work and consent: the XERJ registry.