deltos

Self-hosted Kanban PWA for projects, tasks, shared expenses and passive gamification. Live updates over SSE, comments, attachments…

A new way for AI to search for data
View on GitHub
3GitHub stars

TypeScript, shell

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 58619ce3fa (2026-10-19).

Selected work

Nacho
@gnacho

“Migrate the server and landing to TypeScript”. 47 files, 3,040 lines in server, landing, the project root.

Licence

The repository

AGPL-3.0

Checked by a person at the pinned commit.

The XERJ corpus

Approach only

The author agreed by email on 2026-10-05. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: approach only

Example questions

The prompt

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

Search the GitHub repository gnacho/deltos with XERJ (https://hub.xerj.org/corpus/gnacho--deltos).
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/gnacho/deltos deltos && git -C deltos checkout 58619ce3fa7db7a6e29df7c64fc3936a3f31dc0c
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./deltos --url http://127.0.0.1:9200 --prefix deltos --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: AGPL-3.0. Read it for the approach only, do not copy code.

Related

Selected work and consent: the XERJ registry.