Agent skill · software engineering · aradotso
mac-code-local-ai-agent
Run a free 35B AI coding agent on Apple Silicon Macs using local LLMs via llama.cpp or MLX with web search, shell, and file tools.
Why this skill is useful
Adds executable scripts for running a local AI coding agent with specific configurations and model downloads that aren't widely documented.
What it needs
Requires ddgs, huggingface-hub, llama.cpp, mlx-lm, rich installed locally. About 6k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
mac-code — Free Local AI Agent on Apple Silicon Skill by ara.so — Daily 2026 Skills collection. Run a 35B reasoning model locally on your Mac for $0/month. mac-code is a CLI AI coding agent (Claude Code alternative) that routes tasks — web search, shell commands, file edits, chat — through a local LLM. Supports llama.cpp (30 tok/s) and MLX (64K context, persistent KV cache) backends on Apple Silicon. --- What It Does LLM-as-router: The model classifies every prompt as search, shell, or chat and routes accordingly 35B MoE at 30 tok/s via llama.cpp + IQ2M quantization (fits in 16 GB RAM) 35B full Q4 on 16 GB via custom MoE Expert Sniper (1.54 tok/s, only 1.42 GB RAM used) 9B at 64K context via quantized KV cache (q40 keys/values) MLX backend adds persistent KV cache save/load, context compression, R2 sync Tools: DuckDuckGo search, shell execution, file read/write --- Installation Prerequisites Clone the repo Download models 35B MoE — fast daily driver (10.6 GB, fits in 16 GB RAM): 9B — 64K context, long documents (5.3 GB): --- Starting the Backend Option A: llama.cpp + 35B MoE (recommended, 30 tok/s) Option B: llama.cpp + 9B (64K context) Option C: MLX backend (persistent context, 9B) Start the agent (all options) --- Agent CLI Commands Inside the agent REPL, type / for all commands: Command Action --- --- /agent Agent mode with tools (default) /raw Direct streaming, no tools /model 9b Switch to 9B model (64K context) /model 35b Switch to 35B MoE /search <query> Quick DuckDuckGo search /bench Run speed benchmark /stats Session statistics /cost Show cost savings vs cloud /good / /bad Grade the last response /improve View response grading stats /clear Reset conversation /quit Exit Example prompts --- MLX Backend — Persistent KV Cache API The MLX engine exposes a REST API on localhost:8000. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/mac-code-local-ai-agent