FeiyuNote
小而美的 Android 学习笔记:拍照提问、DeepSeek 讲解、本地复习笔记
A new way for AI to search for data
10GitHub stars
What XERJ indexed
Selected work

“add course handbook, class notes and localized lesson pr…”. 28 files, 1,987 lines in app/src.
Licence
The repository
GPL-3.0
Checked by a person at the pinned commit.
The XERJ corpus
Approach only
The author agreed by email on 2026-10-19. 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
- What does app/src do in FeiyuNote?
The prompt
Paste it into your AI agent. It clones Yongzhaooo/FeiyuNote at the pinned commit and indexes it on your machine.
Search the GitHub repository Yongzhaooo/FeiyuNote with XERJ (https://hub.xerj.org/corpus/yongzhaooo--feiyunote). 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/Yongzhaooo/FeiyuNote FeiyuNote && git -C FeiyuNote checkout 6a79fa7a4e39786e54aa1063765b2c4099088d25 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./FeiyuNote --url http://127.0.0.1:9200 --prefix feiyunote --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: GPL-3.0. Read it for the approach only, do not copy code.
Related
Yongzhao ChenWeb and frontend platform corpora
Selected work and consent: the XERJ registry.