Alex Goulielmos agouliel

The following guide will show you how to connect a local model served with MLX to OpenCode for local coding.

curl -fsSL https://opencode.ai/install | bash

Let's hack on `llm`!

If you have uv installed (and you should!), you can install llm globally in a uv-managed tool environment with:

uv tool install llm

If you want to use models other than OpenAI models, you'll need some extensions:

	#!/bin/bash
	set -eu

	# ── SSM agent ────────────────────────────────────────────────────────────────
	# We need the SSM agent for accessing Lightsail instances
	if ! snap services amazon-ssm-agent \| grep -q 'active'; then
	snap stop amazon-ssm-agent \|\| true
	fi
	/snap/amazon-ssm-agent/current/amazon-ssm-agent -register -y \
	-id "${ssm_activation_id}" \

	import json
	import random
	import mlx.optimizers as optim
	import mlx.core as mx
	import mlx.nn as nn
	import numpy as np

	from tqdm import tqdm
	import time
	from datetime import datetime

	# aproducer.py
	#
	# Async Producer-consumer problem.
	# Challenge: How to implement the same functionality, but no threads.

	import time
	from collections import deque
	import heapq

	class Scheduler:

	# LVDB - LLOOGG Memory DB
	# Copyriht (C) 2009 Salvatore Sanfilippo <antirez@gmail.com>
	# All Rights Reserved

	# TODO
	# - cron with cleanup of timedout clients, automatic dump
	# - the dump should use array startsearch to write it line by line
	# and may just use gets to read element by element and load the whole state.
	# - 'help','stopserver','saveandstopserver','save','load','reset','keys' commands.
	# - ttl with milliseconds resolution 'ttl a 1000'. Check ttl in dump!