AI & LLM infrastructure
GPU nodes, model serving, RAG and MCP integrations, run with real guardrails and observability.
Project
Ask your network questions in plain language, answered from NetBox by a self-hosted LLM.
Builds on NetBox Labs' read-only Model Context Protocol server. The project exposes the server through mcpo as standard OpenAPI endpoints and adds a chatbot that connects it to an internal, OpenAI-compatible LLM, so infrastructure questions can be answered without sending data to a public AI service.
GPU nodes, model serving, RAG and MCP integrations, run with real guardrails and observability.
BGP, SD-WAN, firewalls and VoIP, run through NetBox and automated with Go, Python and Ansible.
Open to select consulting, contract and advisory work. Tell me what you are building and where it hurts.