Projects

A lightweight Proxmox LXC container configured as a Tailscale exit node, enabling secure remote access to home network resources from anywhere.

• Minimal resource footprint using unprivileged LXC container
• Automated setup script for quick deployment
• Secure exit node configuration with Tailscale ACLs
• Enables access to home network services while traveling

A self-hosted AI inference server running Ollama in an LXC container with GPU passthrough for local LLM capabilities.

• GPU passthrough to LXC for accelerated inference
• Multiple LLM models available (Llama, Mistral, CodeLlama)
• API endpoint for integration with other homelab services
• Private and secure local AI without cloud dependencies

This website! Built with Astro and featuring an in-browser LLM for AI-powered resume tailoring.

• In-browser LLM using WebLLM for job description analysis
• Static site generation with Astro
• React islands for interactive components
• Responsive design with custom styling