Hi, I'm

Marcel Rapold

ICT ProjectLead by day, Fullstack AI VibeCoder by night

Welcome to my personal AI development dashboard. Here you'll find access to my locally hosted AI tools and services.

Docker Compose
CUDA 12.1
RTX 5090 32GB
128GB RAM

AI Tools & Services

Professional AI tools for chat, image generation, and workflow automation

Checking...

N8N Workflows

Workflow automation for AI pipelines. Text→Image, batch processing, webhook triggers, and more.

AI PipelinesAutomationWebhooks
Checking...

Ollama API

High-performance LLM API for local language models. Optimized for RTX 5090 with up to 60 tokens/s.

API Access70B ModelsReal-time
Checking...

Open WebUI

Modern chat interface for LLMs with Ollama integration. Supports Llama 3.1, Mistral, Gemma, and more.

Chat InterfaceMulti-ModelHistory
Checking...

Stable Diffusion

AUTOMATIC1111 WebUI for classic SD models, SDXL, LoRAs, and ControlNet. Ready to use out of the box.

SD 1.5/SDXLLoRAsControlNet
Checking...

ComfyUI

Node-based workflow environment for FLUX, Stable Diffusion, and custom pipelines. Batch-processing ready.

WorkflowsFLUXCustom Nodes
Checking...

Portainer

Docker container management with user-friendly web interface. Monitor and manage all containers and services.

Container ManagementDockerMonitoring

Coming Soon

Planned extensions for the AI Development Dashboard

πŸ”Š Audio & Voice

πŸŽ₯ Video & Generative Media

πŸ“Š Data & Analytics

πŸ€– Automation & Agents

πŸ›  DevOps & Infrastructure

πŸ”’ Security & Privacy

πŸ‘¨β€πŸ’» Development Tools

🧠 Knowledge & Documentation

🎨 Creativity & Specialized

Next Steps

Next planned: Grafana + Prometheus for better monitoring

Tech Stack

Powered by RTX 5090 | Self-Hosted | Open Source