Dielldev /
egant
One native desktop window for all your coding agents. Run Claude Code, Codex, opencode and more in your real project folders, with chat…
A new way for AI to search for data
1GitHub stars
What XERJ indexed
Selected work
“Context windows show the wide 1M window on every provider”. 9 files, 357 lines in crates/harness, src/lib, src-tauri.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-21. 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
Example questions
- Where does egant handle “Context windows show the wide 1M window on every provider”?
- What does crates/harness do in egant?
The prompt
Paste it into your AI agent. It clones Dielldev/egant at the pinned commit and indexes it on your machine.
Search the GitHub repository Dielldev/egant with XERJ (https://hub.xerj.org/corpus/dielldev--egant). 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/Dielldev/egant egant && git -C egant checkout 976f6da291e15a3300cedca80bc7785d09cf7ab6 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./egant --url http://127.0.0.1:9200 --prefix egant --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
DielldevAI, prompts and agents corpora
Selected work and consent: the XERJ registry.