repowise

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural…

A new way for AI to search for data
View on GitHub
7,905GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 185c9fd8dc (2026-10-10).

Selected work

“promote PHP to Good tier with complexity, LCOM4, and as…”. 9 files, 369 lines in tests, packages/core.

Licence

The repository

AGPL-3.0

Checked by a person at the pinned commit.

The XERJ corpus

Approach only

The author agreed by email on 2026-10-10. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: approach only

aicode-intelligencedead-codedeveloper-toolsdocumentationgit-analyticsmcpopen-source

Example questions

The prompt

Paste it into your AI agent. It clones repowise-dev/repowise at the pinned commit and indexes it on your machine.

Search the GitHub repository repowise-dev/repowise with XERJ (https://hub.xerj.org/corpus/repowise-dev--repowise).
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/repowise-dev/repowise repowise && git -C repowise checkout 185c9fd8dcd92b7f73d7a7a4437ea241c6df15b6
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./repowise --url http://127.0.0.1:9200 --prefix repowise --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: AGPL-3.0. Read it for the approach only, do not copy code.

Related

Selected work and consent: the XERJ registry.