dale

Natural language to Linux commands. 100% offline. One native binary

A new way for AI to search for data
View on GitHub
3GitHub stars
10commits on main
0forks
v1.1.0latest release, 2026-10-29

C++ 98.7%, CMake 1%, Shell 0.3% · created 2026-10-23 · last push 2026-10-29

What XERJ indexed

Snapshot

113 files · 1.0 MB

The whole repository at commit 063d1a154f (2026-10-29). main is 3 commits ahead.

Selected work

Manuel Garcia Sanz
@manuelgscom

“dale 1.1.0”. 30 files, 2,343 lines in tests, src/cli, the project root.

Licence

The repository

MIT

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

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-30. 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

clicommand-linecppgguflinuxllama-cppllmlocal-llm

Example questions

The prompt

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

Search the GitHub repository manuelgscom/dale with XERJ (https://hub.xerj.org/corpus/manuelgscom--dale).
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/manuelgscom/dale dale && git -C dale checkout 063d1a154f250c34a32cceb3127255eb16e14897
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./dale --url http://127.0.0.1:9200 --prefix dale --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.

Related

Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.