I automate infrastructure and build AI tools: LLM inference on a single RTX 5090, agents with Claude Code, and the Proxmox and Docker stack they run on.
Public repositories on GitHub, most recently pushed first.
Fast LLM server for NVIDIA Blackwell: GeForce RTX 50 and RTX PRO. Qwen3.8-27B on one RTX 5090: 91-94 tok/s, 1.3x vLLM and 1.4x llama.cpp. Runs the 123.6 GiB Qwen3.8-Flash-Next on a 32 GB card. OpenAI and Anthropic API, tool calls, one docker run.
APA: adaptive-precision attention prefill for sm_120a (FP4 pass + exact FP16 hot tiles), MPL-2.0
Local-first AI prompt generator with a Gradio UI: 132 tuned roles for video, image, audio, 3D and creative AI tools. Runs uncensored Dolphin LLMs fully offline, auto-scaled to your GPU VRAM. No API keys, no cloud.
Rejection is the default: an operating manual for a Claude Code session whose job is driving other sessions and refusing anything not backed by evidence
Findet den schnellsten DNS-Resolver vom eigenen Standort aus. Pure stdlib-Python, laeuft im Container.
Recover the CUDA launch and implicit-destructor edges a syntactic indexer loses, written straight into CodeGraph's SQLite graph. On imp (kekzl/imp, 240k lines of C++/CUDA): kernel launch coverage 74.2% → 99.3%, destructors 0% → 85%. On llm.c, which hides nothing, it adds 0 edges.
Eine Honigbiene fliegt im Gegenlicht durch eine Sommerwiese — Echtzeit, WebGL2, ohne Build-Schritt
Monitor Entra ID (Azure AD) application secrets and certificates for expiration. Sends alerts via Email, Teams, Slack, or Webhook before credentials expire.
A living, continually learning neuromorphic being — a spiking neural network in C++23/CUDA with purely local plasticity (STDP, R-STDP, and Feedback Alignment instead of backprop). Runs on RTX 5090.
AI-powered email sorting for MailCow - Generate smart Sieve filters automatically using Claude API or local LLMs
Analyze meeting room usage via Microsoft Graph API with a React + FastAPI dashboard