Local-First AI
Knowledge systems on your own hardware: transparent, inspectable, and nobody else's to revoke.
A Fleet domain · running on the frozen substrate
The problem it answers
Cloud-hosted AI puts your knowledge behind someone else's infrastructure, pricing, and policies.
Why it matters
Understanding you can't run without permission isn't yours. Local-first keeps the whole loop under your control.
6 Fleet Deployments
The deployments
Open on GitHub. Every system below runs on the same frozen decision substrate — this domain is one more proof that the substrate never needed editing.
turboq
activeComprehensive local LLM inference platform that synthesizes research-grade KV cache optimization, graph-based agent orchestration, and distributed cluster deployment into a unified system.
Go
github.com/kliewerdaniel/turboq →sovereign-scaffold
activeDeployable, configurable sovereign AI system that you can run locally and deploy for any client.
Python
github.com/kliewerdaniel/sovereign-scaffold →sovereign
productionLocal-first AI operating system. No cloud. No telemetry. Your inference. Your memory. Your governance.
Python
github.com/kliewerdaniel/sovereign →sse
activeLocal-first, privacy-focused Sovereign Intelligence Layer that eliminates dependency on cloud-based AI services.
Python
github.com/kliewerdaniel/sse →rlm
activeGeneral plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
Python
github.com/kliewerdaniel/rlm →ollama-chatbot
experimentalExperimental Ollama integration for chatbot applications.
Python
github.com/kliewerdaniel/ollama-chatbot →