cavi-ai /

mlx-workbench

Prepare, check and serve local models on Apple Silicon from a native macOS app powered by MLX Agent

A new way for AI to search for data
View on GitHub
2GitHub stars

Swift

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit fa600a19e3 (2026-10-17).

Selected work

Sasan
@sasan1200

“add library empty-state actions”. 13 files, 1,442 lines in mlx-mac.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-19. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

mlxllmlocal-firstpythonapple-silicongguflocal-llmmacos

Example questions

The prompt

Paste it into your AI agent. It clones cavi-ai/mlx-workbench at the pinned commit and indexes it on your machine.

Search the GitHub repository cavi-ai/mlx-workbench with XERJ (https://hub.xerj.org/corpus/cavi-ai--mlx-workbench).
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/cavi-ai/mlx-workbench mlx-workbench && git -C mlx-workbench checkout fa600a19e34e9ae8367d26c5c86c9bd15c45240d
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./mlx-workbench --url http://127.0.0.1:9200 --prefix mlx-workbench --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

SasanAI, prompts and agents corporamkcertdunorth595--ai-agent-chatdunorth595--ai-agent-memoryaosama/astronomicalNehharShah/dfmraspoli/mlx-serve

Selected work and consent: the XERJ registry.