Jeecabs /

whiskd

Lightweight process wrapper with a TUI status bar for agents and humans

A new way for AI to search for data

View on GitHub

2GitHub stars

Rust, shell

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 6700b20f2e (2026-09-30).

Selected work

L Jacobs
@Jeecabs

“rewrite whiskd in Rust (5.0.0)”. 7 files, 2,880 lines in src, the project root.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-20. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

agentsclilogsprocess-managertui

Example questions

How does whiskd implement agents?
Where does whiskd handle “rewrite whiskd in Rust (5.0.0)”?
Show the cli code in whiskd.

The prompt

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

Search the GitHub repository Jeecabs/whiskd with XERJ (https://hub.xerj.org/corpus/jeecabs--whiskd).
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/Jeecabs/whiskd whiskd && git -C whiskd checkout 6700b20f2e1bb08ad9ee77c8de6e9a0c9332fe0b
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./whiskd --url http://127.0.0.1:9200 --prefix whiskd --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.

L Jacobs Web and frontend platform corpora chroma xerj-blogposts fluent-bit ntatschner/loadout-cli AnonMohak/dakken dzkchen/oh-my-diff

Selected work and consent: the XERJ registry.