nfind

Find files by describing them in natural language, auto-generate an equivalent script, and run it in sandboxed containers

A new way for AI to search for data

View on GitHub

1GitHub stars

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 775bcc7f49.

Selected work

Dinu Gherman
@deeplook

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-11-11. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

dockerfilesfindllmnatural-languagesandboxsearchnerdctl

Example questions

How does nfind implement docker?
Show the files code in nfind.

The prompt

Paste it into your AI agent. It clones deeplook/nfind at the pinned commit and indexes it on your machine.

Search the GitHub repository deeplook/nfind with XERJ (https://hub.xerj.org/corpus/deeplook--nfind).
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/deeplook/nfind nfind && git -C nfind checkout 775bcc7f4930592e2d96577eebcf546519f08202
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./nfind --url http://127.0.0.1:9200 --prefix nfind --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.

Dinu Gherman Security and vulnerabilities corpora openlegaldata-oldp dagger retext-passive devcell-sh/devcell google/gvisor andreimerlescu/roc

Selected work and consent: the XERJ registry.