ai-infra-bench

End-to-end automated benchmarking for AI infrastructure workflows

A new way for AI to search for data
View on GitHub
6GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit eec792884a (2026-10-19).

Selected work

Muqi Li
@Muqi1029

“refactor & support aib tokenize”. 6 files, 737 lines in tests, ai_infra_bench, test.

Licence

The repository

Apache-2.0

Checked by a person at the pinned commit.

The XERJ corpus

Apache-2.0, with credit

The author agreed by email on 2026-10-20. 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

The prompt

Paste it into your AI agent. It clones Muqi1029/ai-infra-bench at the pinned commit and indexes it on your machine.

Search the GitHub repository Muqi1029/ai-infra-bench with XERJ (https://hub.xerj.org/corpus/muqi1029--ai-infra-bench).
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/Muqi1029/ai-infra-bench ai-infra-bench && git -C ai-infra-bench checkout eec792884a177be55c488a11243fc9a2fde8b930
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./ai-infra-bench --url http://127.0.0.1:9200 --prefix ai-infra-bench --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: Apache-2.0. Keep the copyright notice and credit the authors.

Related

Selected work and consent: the XERJ registry.