Hey, I'm Raph
Running the IT infrastructure @ EIFER and building AI tools with Claude Code on the side.
Writing about CUDA and AI infrastructure at rfriedmann.de.
Projects
AI tools, infrastructure automation, and open source utilities.
imp
High-performance LLM inference engine in C++/CUDA for NVIDIA Blackwell (RTX 5090/5080/5070 Ti, RTX PRO 6000; sm_120). Native NVFP4/GGUF, 270 tok/s decode on Qwen3-Coder-30B MoE. Written entirely by Claude Code.
PromptMill
AI-powered prompt generator for video (Wan2.1/2.2, Hunyuan), image (SD, FLUX, Midjourney, DALL-E), and creative content. Local LLMs with GPU auto-detection.
seedling
Open-source synthetic instruction dataset generator for SFT with local LLMs. Generate, curate, and export instruction-response pairs using Ollama.
mailcow-ai-filter
AI-powered email sorting for MailCow - Generate smart Sieve filters automatically using Claude API or local LLMs
entra-id-secrets-notification
Monitor Entra ID (Azure AD) application secrets and certificates for expiration. Sends alerts via Email, Teams, Slack, or Webhook before credentials expire.
MeetingRoomUsageAnalyzer
Analyze meeting room usage via Microsoft Graph API with a React + FastAPI dashboard
mcp-docker-examples
On-demand MCP servers using Docker Compose profiles - solve the context-eating problem