Roy Zhu

Corpus Hub contributor since 2026-10-29

Roy Zhu'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

15files

827lines

★ 31GitHub stars on repo

Totals across every corpus @royisme 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 pikabaka corpus

royisme/pikabaka: Open-source AI interview copilot & meeting assistant. Real-time transcription, AI-suggested answers, screenshot reasoning. BYO API key, or…

Look up how pikabaka implements ai, ai-assistant, claude, with answers cited to file and line.
Reuse a worked example: the commit “edit the role and task prompts in Settings” (15 files · TypeScript).
Answer from pikabaka's real TypeScript source instead of memory (AI, prompts and agents).

Example questions

Where does pikabaka handle “edit the role and task prompts in Settings”?
How does pikabaka implement ai?
What does test do in pikabaka?

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

Search the GitHub repository royisme/pikabaka with XERJ (https://hub.xerj.org/corpus/royisme--pikabaka).
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/royisme/pikabaka pikabaka && git -C pikabaka checkout ecbec37f3cab536cfebe0cc44154b6787d328a7a
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./pikabaka --url http://127.0.0.1:9200 --prefix pikabaka --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: AGPL-3.0. Read it for the approach only, do not copy code.

corpus royisme--pikabaka · AI, prompts and agents
Related corpora: griptape, agentops, ThinkInAIXYZ/deepchat, sotger/allai-chat
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 31

royisme/pikabaka

Open-source AI interview copilot & meeting assistant. Real-time transcription, AI-suggested answers, screenshot reasoning. BYO API key, or run fully offline with Ollama. macOS + Windows

On GitHub: 408 commits · 9 forks · created 2026-03 · last push 2026-10-31

Languages: TypeScript 94%, Rust 4%, JavaScript 2%

ecbec37f3c feat(prompt): edit the role and task prompts in Settings

selected commit: 15 files · 827 lines · TypeScript · test, electron, src/components

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

live on the hub · licence clearedcorpus royisme--pikabakaAIAGPL-3.0aiai-assistantclaudecluely-alternativeelectrongemini agreed 2026-10-29

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

Included with the author's permission (email, 2026-10-29), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.