lightward-ai

for whatever's real

A new way for AI to search for data
View on GitHub
9GitHub stars

Ruby, JavaScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 8e25cfa85c (2026-10-11).

Selected work

Isaac Bowen
@isaacbowen

“sonnet 5.5”. 7 files, 603 lines in spec, app/javascript, app/lib.

Licence

The repository

Unlicense

Checked by a person at the pinned commit.

The XERJ corpus

Unlicense, 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

Example questions

The prompt

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

Search the GitHub repository lightward/lightward-ai with XERJ (https://hub.xerj.org/corpus/lightward--lightward-ai).
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/lightward/lightward-ai lightward-ai && git -C lightward-ai checkout 8e25cfa85cebefa046f81111d77243981a830baa
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./lightward-ai --url http://127.0.0.1:9200 --prefix lightward-ai --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: Unlicense. Keep the copyright notice and credit the authors.

Related

Selected work and consent: the XERJ registry.