Brian Yuan

What an agent can do with the OpenShelf corpus

brian4685380/OpenShelf: Native macOS floating shelves for files, images, text, and links. Collect, arrange, and drag anywhere

• Look up how OpenShelf implements appkit, drag-and-drop, homebrew, with answers cited to file and line.
• Reuse a worked example: the commit “Make CLI delivery recoverable with a private expiring request queue” (6 files · Swift, Ruby).
• Answer from OpenShelf's real Swift source instead of memory (AI, prompts and agents).

• Where does OpenShelf handle “Make CLI delivery recoverable with a private expiring request queue”?
• How does OpenShelf implement appkit?
• What does sources do in OpenShelf?

Search the GitHub repository brian4685380/OpenShelf with XERJ (https://hub.xerj.org/corpus/brian4685380--openshelf).
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/brian4685380/OpenShelf OpenShelf && git -C OpenShelf checkout 064a83807cf24cd07e64a4ff847bc453253a023d
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./OpenShelf --url http://127.0.0.1:9200 --prefix openshelf --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 brian4685380--openshelf · AI, prompts and agents
Related corpora: mkcert, swift-book, jeso87/Patchy-UI, nparashar150/dockset
AI search and retrieval with XERJ · Case study: reference coding for agents