lightspeed-stack

LLM tooling stack

A new way for AI to search for data

View on GitHub

40GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 0f2b012c0b (2026-10-15).

Selected work

asimurka
@asimurka

“Implemented abstract inference provider class”. 5 files, 522 lines in src/providers, tests.

Licence

The repository

Apache-2.0

Checked by a person at the pinned commit.

The XERJ corpus

Apache-2.0, with credit

The author agreed by email on 2026-10-24. 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 lightspeed-stack handle “Implemented abstract inference provider class”?
What does src/providers do in lightspeed-stack?

The prompt

Paste it into your AI agent. It clones lightspeed-core/lightspeed-stack at the pinned commit and indexes it on your machine.

Search the GitHub repository lightspeed-core/lightspeed-stack with XERJ (https://hub.xerj.org/corpus/lightspeed-core--lightspeed-stack).
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/lightspeed-core/lightspeed-stack lightspeed-stack && git -C lightspeed-stack checkout 0f2b012c0b6979f1ecd372a5ebc9b963d61adbac
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./lightspeed-stack --url http://127.0.0.1:9200 --prefix lightspeed-stack --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: Apache-2.0. Keep the copyright notice and credit the authors.

asimurka AI, prompts and agents corpora

Selected work and consent: the XERJ registry.