rangwea /
swallow
A cool static blog client base on wails in golang
A new way for AI to search for data
31GitHub stars
What XERJ indexed
Selected work
“Upgrade Hugo integration and improve settings persistence”. 31 files, 1,451 lines in backend, frontend, the project root.
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 2026-10-20. 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
bloggolangguireactwailshugo
Example questions
- How does swallow implement blog?
- Where does swallow handle “Upgrade Hugo integration and improve settings persistence”?
- What does backend do in swallow?
The prompt
Paste it into your AI agent. It clones rangwea/swallow at the pinned commit and indexes it on your machine.
Search the GitHub repository rangwea/swallow with XERJ (https://hub.xerj.org/corpus/rangwea--swallow). 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/rangwea/swallow swallow && git -C swallow checkout 1b4bdd0ceb3f72175cdd65f2f761cdf9c7e39e6b 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./swallow --url http://127.0.0.1:9200 --prefix swallow --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
wikiaWeb and frontend platform corporaesbuildprotovalidategolang-x-cryptolucasdillmann/nginx-ignitionTanvirul-swe/vetrologArkGravity/burrow
Selected work and consent: the XERJ registry.