reconD

A lightweight container deployment agent that continuously reconciles desired and observed state, inspired by Kubernetes controllers and…

A new way for AI to search for data
View on GitHub
5GitHub stars

Go

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit d4fc02ec15 (2026-10-12).

Selected work

Tobi Odeyemi
@ercross

“bound forward and rollback deployment attempts”. 12 files, 1,326 lines in deployment, state, config.

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

automationcontainercontinuous-deliverycontrollerdeploymentdesired-statedevopsgitops

Example questions

The prompt

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

Search the GitHub repository ercross/reconD with XERJ (https://hub.xerj.org/corpus/ercross--recond).
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/ercross/reconD reconD && git -C reconD checkout d4fc02ec15c71116cb534762117b1a8dee240196
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./reconD --url http://127.0.0.1:9200 --prefix recond --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.

Related

Selected work and consent: the XERJ registry.