Skip to main content

Vera — Local LLM Stack

Vera hosts local AI/LLM tooling used for development assistance and infrastructure automation.

Current Setup

Placeholder — document installed models, APIs, and tools as they are confirmed.

Common Tools

ToolPurpose
OllamaLocal LLM inference
Windsurf / CascadeAI-assisted coding
Python scriptsAutomation and data tasks

Notes

  • Local LLM inference runs entirely on Vera — no data leaves to external services
  • Models and configuration to be documented as stack stabilises