dsh-code-index

Local code intelligence for DSH: task-aware source context packs with relationships, changes, likely tests, and hard budgets

A new way for AI to search for data
View on GitHub
10GitHub stars

TypeScript, JavaScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 1158f541ff (2026-10-12).

Selected work

lemonxiny55
@lemonxiny55

“add pinned ArkTS parsing and reliable code context”. 19 files, 613 lines in tests, src, grammars.

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

code-indexdeepseek-harnessdsh-plugintree-sittercall-graphcode-intelligencecode-searchrepo-map

Example questions

The prompt

Paste it into your AI agent. It clones lemonxiny55/dsh-code-index at the pinned commit and indexes it on your machine.

Search the GitHub repository lemonxiny55/dsh-code-index with XERJ (https://hub.xerj.org/corpus/lemonxiny55--dsh-code-index).
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/lemonxiny55/dsh-code-index dsh-code-index && git -C dsh-code-index checkout 1158f541ff07db052fbd1c221022b8c8816b389d
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./dsh-code-index --url http://127.0.0.1:9200 --prefix dsh-code-index --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

Selected work and consent: the XERJ registry.