mmtk

An experimental toolkit of metamath based on mmj2

A new way for AI to search for data
View on GitHub
2GitHub stars

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 8d761c4934.

Selected work

Mingli Yuan
@mountain

Licence

The repository

GPL-2.0

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

The XERJ corpus

Approach only

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-11-10. 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

metamathverficationmathmathematics

Example questions

The prompt

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

Search the GitHub repository mountain/mmtk with XERJ (https://hub.xerj.org/corpus/mountain--mmtk).
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/mountain/mmtk mmtk && git -C mmtk checkout 8d761c49341f5f5a1c7164e40029abf404c138a7
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./mmtk --url http://127.0.0.1:9200 --prefix mmtk --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: GPL-2.0. Read it for the approach only, do not copy code.

Related

Selected work and consent: the XERJ registry.