jtmckay /

decree

Durable state-machine (AI) workflows from plain files

A new way for AI to search for data

View on GitHub

3GitHub stars

Rust

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 2349301082 (2026-10-19).

Selected work

Taylor
@jtmckay

“A06: `max_depth` defaults to 10 and can be changed (A06-max-depth-set…”. 12 files, 659 lines in tests, src, src/commands.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-24. 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

What does src/commands do in decree?

The prompt

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

Search the GitHub repository jtmckay/decree with XERJ (https://hub.xerj.org/corpus/jtmckay--decree).
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/jtmckay/decree decree && git -C decree checkout 234930108263dbc6d7d37caa299ab00c06c6a703
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./decree --url http://127.0.0.1:9200 --prefix decree --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.

Taylor AI, prompts and agents corpora

Selected work and consent: the XERJ registry.