codex

A fast, lightweight embedded key-value database for Go: encrypted, crash-safe, concurrent, and built for simple persistent storage

A new way for AI to search for data
View on GitHub
1GitHub stars

Go

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 44a4b93fb6 (2026-10-22).

Selected work

“Refactor project structure: rename `codex/src` to `app`, update docum…”. 10 files, 1,386 lines in app/storage, app, app/integrity.

Licence

The repository

MPL-2.0

Checked by a person at the pinned commit.

The XERJ corpus

Approach only

The author agreed by email on 2026-10-23. 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

Example questions

The prompt

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

Search the GitHub repository evertonmj/codex with XERJ (https://hub.xerj.org/corpus/evertonmj--codex).
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/evertonmj/codex codex && git -C codex checkout 44a4b93fb632f46fc88167716e7f471738bf5806
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./codex --url http://127.0.0.1:9200 --prefix codex --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: MPL-2.0. Read it for the approach only, do not copy code.

Related

Selected work and consent: the XERJ registry.