zerry

What an agent can do with the garu corpus

ongjin/garu: 초경량 한국어 형태소 분석기: 1MB 모델로 브라우저에서 실행(WASM). Ultra-lightweight Korean morphological analyzer in the browser. npm: garu-ko

• Look up how garu implements browser, hangul, korean, with answers cited to file and line.
• Reuse a worked example: the commit “탐색 전 아크 비용 보정(Section 18)과 구어 판별 게이트: 연구 브랜치” (10 files · Rust, Python).
• Answer from garu's real Rust source instead of memory (Web and frontend platform).

• Where does garu handle “탐색 전 아크 비용 보정(Section 18)과 구어 판별 게이트: 연구 브랜치”?
• How does garu implement browser?
• What does crates/garu-core do in garu?

Search the GitHub repository ongjin/garu with XERJ (https://hub.xerj.org/corpus/ongjin--garu).
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/ongjin/garu garu && git -C garu checkout 9dc18b05daca9d868bf66a274b2389477a2f768d
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./garu --url http://127.0.0.1:9200 --prefix garu --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: Apache-2.0. Keep the copyright notice and credit the authors.

corpus ongjin--garu · Web and frontend platform
Related corpora: flexrag, covid-qa, uiwwsw/virtual-keyboard, AlgoBrother/MayaTok-BPE
Case study: reference coding for agents