Leonid Shirmanov shirmanov

April 2026 TLDR setup for Ollama + Gemma 4 on a Mac mini (Apple Silicon) — auto-start, preload, and keep-alive

April 2026 TLDR Setup for Ollama + Gemma 4 on a Mac mini (Apple Silicon)

Prerequisites

Mac mini with Apple Silicon (M1/M2/M3/M4/M5)
At least 16GB unified memory for Gemma 4 (default 8B)
macOS with Homebrew installed

Architectural Comparison: Claude Flow V3 vs Claude Code TeammateTool

Date: 2026-01-25 Analysis: Side-by-side comparison of Claude Flow V3 swarm architecture (developed by rUv) and Claude Code's TeammateTool (discovered in v2.1.19)

Executive Summary

A detailed analysis reveals striking architectural similarities between Claude Flow V3's swarm system and Claude Code's TeammateTool. The terminology differs, but the core concepts, data structures, and workflows are nearly identical.

Claude Code TeammateTool - Source Code Analysis

This is not a proposal. This documents existing but hidden functionality found in Claude Code v2.1.19 binary, plus speculation on how it could be used.

Executive Summary

TeammateTool already exists in Claude Code. We extracted this from the compiled binary at ~/.local/share/claude/versions/2.1.19 using strings analysis. The feature is fully implemented but gated behind feature flags (I9() && qFB()).

Inferal Workspace Architecture: How We Work at Inferal

(Blog version available at https://inferal.com/blog/workspace-architecture/)

Update: Inferal Workspace is going open source!

Your org's brain that AI can use

This is not our core product. This document describes our internal operating environment - how we run the company. We share it to show the environment you'd join and demonstrate our philosophy in action. For what we're building, see What We're Building below.

	use active_call::media::engine::StreamEngine;
	use active_call::media::processor::Processor;
	use active_call::media::track::TrackPacketSender;
	use active_call::media::{AudioFrame, Samples, TrackId};
	use anyhow::Result;
	use axum::body::Body;
	use axum::extract::Path;
	use axum::response::{IntoResponse, Response};
	use bytes::Bytes;
	use flate2::Compression;

	# Base image for Copilot CLI sandbox
	FROM docker/sandbox-templates:copilot

	USER root

	# CUSTOMIZE: Install system-level dependencies your project needs.
	# Examples:
	# Python/Flask:
	# RUN apt-get update && apt-get install -y --no-install-recommends \
	# python3-flask python3-sqlalchemy && rm -rf /var/lib/apt/lists/*

	"""
	The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp

	#!/usr/bin/env python3
	"""
	DeepSeek-OCR-2 markdown extraction for olmocr-bench.

	Generates markdown files from images. For scoring, see: https://github.com/allenai/olmocr

	config:
	Prompt: "<image>\n<\|grounding\|>Convert the document to markdown."
	Repeats: 3


	╭─── Claude Code v2.1.12 ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
	│ │ Tips for getting started │
	│ Welcome back Jonny! │ Run /init to create a CLAUDE.md file with instructions for Claude │
	│ │ │
	│ │ ───────────────────────────────────────────────────────────────── │
	│ ▐▛███▜▌ │ Recent activity

	# Create a new worktree and branch from within current git directory.
	ga() {
	if [[ -z "$1" ]]; then
	echo "Usage: ga [branch name]"
	exit 1
	fi

	local branch="$1"
	local base="$(basename "$PWD")"
	local path="../${base}--${branch}"