Jaull

Evidence-driven qualification and validation of local LLM deployments

A new way for AI to search for data

View on GitHub

3GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 062765ac66 (2026-10-17).

Selected work

Ton Llop
@Ton-Llop

“corregeix Speed i el flux de resultats”. 23 files, 2,645 lines in tests, validation, scripts.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-17. 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

benchmarkingggufgguf-modelshardware-detectionhuggingfacellama-cppllmlocal-ai

Example questions

How does Jaull implement benchmarking?
Where does Jaull handle “corregeix Speed i el flux de resultats”?
What does validation do in Jaull?

The prompt

Paste it into your AI agent. It clones Ton-Llop/Jaull at the pinned commit and indexes it on your machine.

Search the GitHub repository Ton-Llop/Jaull with XERJ (https://hub.xerj.org/corpus/ton-llop--jaull).
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/Ton-Llop/Jaull Jaull && git -C Jaull checkout 062765ac666a0fc885d488a89ac6767ea6fbba16
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./Jaull --url http://127.0.0.1:9200 --prefix jaull --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.

Ton Llop AI, prompts and agents corpora griptape anything-llm graphrag StartLuxLabs/StartLux-Decision MakazhanAlpamys/Soup dynalm-project/dynalm

Selected work and consent: the XERJ registry.