AndrewAltimit

AI Toolkit MCP Server (local diffusion AI model trainer)

Warning: Requires a powerful GPU!

A containerized AI Toolkit setup with MCP (Model Context Protocol) integration for training LoRA models and fine-tuning diffusion models. This provides a complete solution for training custom LoRA models with full MCP integration, allowing AI assistants to manage the entire training workflow.

Note: This pairs well with the ComfyUI MCP Server used for creating images/videos from the trained models

• ComfyUI MCP Server

Features

• Fully Containerized: AI Toolkit and MCP server run in Docker containers

AndrewAltimit

ComfyUI MCP Server (local image/video generation)

Warning: Requires a powerful GPU!

A containerized ComfyUI setup with MCP (Model Context Protocol) integration for AI-driven image generation workflows. Includes both standard MCP (stdio) access and HTTP API access.

Note: This pairs well with the model training mcp used for creating checkpoints / loras

• Train Models MCP Server

Features

AndrewAltimit

Managing GitHub Secrets via Terraform

This example shows how to add a secret to an existing GitHub environment using Terraform.

Do not do this if you are concerned about the secret being stored in the tfstate files. In some scenarios (secret migration from CloudBees -> GitHub) terraform is a reasonable approach to get the job done since it's a one time operation and the state can be thrown away, but for standard long-term secrets management there are other ways to handle it without exposing secrets to state.

Prerequisites

• GitHub repository with existing environments (e.g., PROD, STAGING)
• GitHub personal access token with repo scope

AndrewAltimit

MCP Server LaTeX Integration

A complete implementation guide for integrating LaTeX document compilation with MCP (Model Context Protocol) servers, enabling AI assistants to create professional documents, academic papers, and typeset materials programmatically.

Example Output

UE5 Nanite System LaTeX PDF ( source tex file )

DnD Mechanics PDF ( source tex file )

AndrewAltimit

MCP Server Manim Integration

A complete implementation guide for integrating Manim (Mathematical Animation Engine) with MCP (Model Context Protocol) servers, enabling AI assistants to create programmatic animations and visualizations.

🖼️ Example Output

AndrewAltimit

GitHub Repository Complete Backup

A Docker-based solution to create complete backups of private GitHub repositories, including all branches, history, and LFS files.

What's Included in the Backup

• ✅ All branches and tags
• ✅ Complete commit history
• ✅ All Git LFS files
• ✅ All refs and remote tracking info

AndrewAltimit

Git Workflow Guide

Diagram credit: nikkiandchris.io (@nikki.and.chris, @NikkiSiapno, @ChrisStaud)

A visual guide to understanding Git's core workflow and the relationship between your working directory, staging area, local repository, and remote repository.

AndrewAltimit

Gemini CLI Integration for Claude Code MCP Server

A complete setup guide for integrating Google's Gemini CLI with Claude Code through an MCP (Model Context Protocol) server. This provides automatic second opinion consultation when Claude expresses uncertainty or encounters complex technical decisions.

🚀 Quick Start

AndrewAltimit

Claude Code Git Integration

WARNING: CLAUDE CODE RUNS UNRESTRICTED - USE AT YOUR OWN RISK!

It is recommended to run this in an isolated sandbox environment like a VM with a github personal access token scoped to the bare minimum.

Overview

AndrewAltimit

Setup ai-toolkit for training Flux/Flex loras and using FlowMatch sampler

Step 1: Setup CUDA

Use the latest CUDA version supported by PyTorch: https://pytorch.org/get-started/locally/

CUDA Downloads: https://developer.nvidia.com/cuda-toolkit-archive

Note: CUDA may require NVIDIA App, launch GeForce Experience to upgrade to NVIDIA App. Also CUDA install may require a reboot.