Shobhit Gupta

What an agent can do with the notdrive corpus

SegwiseHQ/notdrive: Notion-style organization layer for Google Drive. Tree-organized pages, tags, smart views, per-user privacy, full-text search across files…

• Look up how notdrive implements collaboration, docker, drizzle, with answers cited to file and line.
• Reuse a worked example: the commit “Add direct PDF export for documents” (4 files · TypeScript).
• Answer from notdrive's real TypeScript source instead of memory (Databases and storage engines).

• Where does notdrive handle “Add direct PDF export for documents”?
• How does notdrive implement collaboration?
• What does apps/web do in notdrive?

Search the GitHub repository SegwiseHQ/notdrive with XERJ (https://hub.xerj.org/corpus/segwisehq--notdrive).
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/SegwiseHQ/notdrive notdrive && git -C notdrive checkout 660b381c2106823e6b5d24a984902129adff5ce8
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./notdrive --url http://127.0.0.1:9200 --prefix notdrive --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 segwisehq--notdrive · Databases and storage engines
Related corpora: xobotyi--cc-foundry-infrastructure, lexbuild, ognjenmarcheta/kaine-forge, workhold/doca
Case study: reference coding for agents