Skip to main content

Open-source software for running AI you own.

Tools to run models on your own hardware, know what they cost, and trust what you are running. Apache-2.0, built in the open, from a small independent company in Gig Harbor, Washington.

projects ↓ github.com/defilantech →

Projects

all Apache-2.0
  • LLMKube

    Run LLM inference on Kubernetes, across NVIDIA, AMD and Apple Silicon. A project I created and lead, built with a growing community of contributors.

    v0.10.19 llmkube.com →

  • Socair

    Signed, fileable assurance reports for open-weight models, before they reach production.

    v0.1.0-rc.9 · pre-release socair.ai →

  • InferCost

    Know what every inference request costs on your own hardware, from GPU amortization to electricity.

    v0.6.0 infercost.ai →

Also from Defilan Technologies: MyGridCheck, power outage tracking for the Puget Sound region →

About

Christopher Maher

Christopher Maher founded Defilan Technologies to build open-source infrastructure for running AI on hardware you control. He created LLMKube and leads its maintainers, and has spent 20+ years in platform and infrastructure engineering.

GitHub LinkedIn X

Contact

For collaboration, sponsorship, or support for any of the projects: contact@defilan.com