CodexChat-

OpenAI Codex VS Code 扩展的本地会话伴生管理器。它读取本机.codex 数据目录，按会话中的 cwd 将历史会话归入项目文件夹。

A new way for AI to search for data

View on GitHub

5GitHub stars

TypeScript, JavaScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 57dbcbccc7 (2026-10-10).

Selected work

MathsionYang
@MathsionYang

“add persistent pins and confirmed deletion in 0.1.9”. 17 files, 1,342 lines in test, src, media.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-20. 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

Where does CodexChat- handle “add persistent pins and confirmed deletion in 0.1.9”?
What does media do in CodexChat-?

The prompt

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

Search the GitHub repository MathsionYang/CodexChat- with XERJ (https://hub.xerj.org/corpus/mathsionyang--codexchat).
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/MathsionYang/CodexChat- CodexChat- && git -C CodexChat- checkout 57dbcbccc7f2ab95f8f119808eb7dc6e2a856d1c
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./CodexChat- --url http://127.0.0.1:9200 --prefix codexchat --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.

MathsionYang AI, prompts and agents corpora

Selected work and consent: the XERJ registry.