JayShen

Corpus Hub contributor since 2026-10-19

JayShen's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.

1corpus

1selected commit

7files

166lines

★ 20GitHub stars on repo

Totals across every corpus @shenjiecode appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.

What an agent can do with the pi-wechat-assistant corpus

shenjiecode/pi-wechat-assistant: 在微信里继续你的 pi 对话。Continue your pi conversation from WeChat: tasks, replies, images, and files

Look up how pi-wechat-assistant implements ai-agent, coding-agent, pi-extension, with answers cited to file and line.
Reuse a worked example: the commit “restore configurable receipt notifications” (7 files · TypeScript).
Answer from pi-wechat-assistant's real TypeScript source instead of memory (AI, prompts and agents).

Example questions

Where does pi-wechat-assistant handle “restore configurable receipt notifications”?
How does pi-wechat-assistant implement ai-agent?
What does tests do in pi-wechat-assistant?

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

Search the GitHub repository shenjiecode/pi-wechat-assistant with XERJ (https://hub.xerj.org/corpus/shenjiecode--pi-wechat-assistant).
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/shenjiecode/pi-wechat-assistant pi-wechat-assistant && git -C pi-wechat-assistant checkout 13f893869385d44e8937f857e2cbd3e835d132df
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./pi-wechat-assistant --url http://127.0.0.1:9200 --prefix pi-wechat-assistant --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.

corpus shenjiecode--pi-wechat-assistant · AI, prompts and agents
Related corpora: atoma-run--atoma, lexbuild, dingdinglz/pi-worktree, Xuxyyy/terminal-coding-agent
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 20

shenjiecode/pi-wechat-assistant

13f8938693 fix: restore configurable receipt notifications (#22)

selected commit: 7 files · 166 lines · TypeScript · tests, src/extension, src/bridge

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

selected · in licence reviewcorpus shenjiecode--pi-wechat-assistantAIMITai-agentcoding-agentpi-extensiontypescriptwechat agreed 2026-10-19

Not installable yet: this corpus is not in the hub registry until its licence review passes, so xerj corpus add and xerj ask cannot fetch it. It becomes installable when this card says live in the hub.

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/shenjiecode/badge.svg)](https://hub.xerj.org/contributors/shenjiecode)

Included with the author's permission (email, 2026-10-19), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.