Chasen Liao

Corpus Hub contributor since 2026-10-11

Chasen Liao'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

22files

853lines

★ 328GitHub stars on repo

Totals across every corpus @Chasen-Liao 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-agent-desktop corpus

Chasen-Liao/pi-agent-desktop: Pi Agent Desktop: 基于 Electron 的 Pi 编程智能体桌面客户端 (衍生自 pi-web)

Look up how pi-agent-desktop implements agent, pi, pi-agent, with answers cited to file and line.
Reuse a worked example: the commit “upgrade Pi to 0.99.1 with native MCP and Codemode controls” (22 files · TypeScript).
Answer from pi-agent-desktop's real TypeScript source instead of memory (AI, prompts and agents).

Example questions

Where does pi-agent-desktop handle “upgrade Pi to 0.99.1 with native MCP and Codemode controls”?
How does pi-agent-desktop implement agent?
What does lib do in pi-agent-desktop?

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

Search the GitHub repository Chasen-Liao/pi-agent-desktop with XERJ (https://hub.xerj.org/corpus/chasen-liao--pi-agent-desktop).
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/Chasen-Liao/pi-agent-desktop pi-agent-desktop && git -C pi-agent-desktop checkout df62fad27d5c20493fc9ef2b4ee7d445285872a1
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./pi-agent-desktop --url http://127.0.0.1:9200 --prefix pi-agent-desktop --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 chasen-liao--pi-agent-desktop · AI, prompts and agents
Related corpora: autorag, cognita, AgwaB/pi-workflow, Chang-Yo/Dela
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 328

Chasen-Liao/pi-agent-desktop

df62fad27d feat: upgrade Pi to 0.99.1 with native MCP and Codemode controls

selected commit: 22 files · 853 lines · TypeScript · lib, components, the project root

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

selected · in licence reviewcorpus chasen-liao--pi-agent-desktopAIMITagentpipi-agent agreed 2026-10-11

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/Chasen-Liao/badge.svg)](https://hub.xerj.org/contributors/Chasen-Liao)

Included with the author's permission (email, 2026-10-11), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.