dfm

A local coding agent for Apple Silicon: edits, builds, tests and verifies code with on-device models (Apple FM + MLX). No remote inference

A new way for AI to search for data

View on GitHub

0GitHub stars

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 7413c5c7d8.

Selected work

Nihar Shah
@NehharShah

Licence

The repository

MIT

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

The XERJ corpus

MIT, with credit

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-11-01. 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

apple-siliconcoding-agentlocal-llmmacosmlxpython

Example questions

How does dfm implement apple-silicon?
Show the coding-agent code in dfm.

The prompt

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

Search the GitHub repository NehharShah/dfm with XERJ (https://hub.xerj.org/corpus/nehharshah--dfm).
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/NehharShah/dfm dfm && git -C dfm checkout 7413c5c7d89583ab0524425a3db51444eb2c1afe
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./dfm --url http://127.0.0.1:9200 --prefix dfm --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.

Nihar Shah AI, prompts and agents corpora xobotyi--cc-foundry-the-coder mkcert xobotyi--cc-foundry-ai-helpers-prompt-engineering raspoli/mlx-serve aosama/astronomical cavi-ai/mlx-workbench

Selected work and consent: the XERJ registry.

dfm