← Back to Architecture
Foundation
⬇Local inference and model execution. The base layer where intelligence runs on your hardware.
Problem
AI systems depend on cloud infrastructure. Local inference provides sovereignty.
Why It Matters
Everything above depends on local-first inference. If you can't run intelligence locally, you have no sovereignty.
4 Projects in Foundation
turboq
Comprehensive local LLM inference platform that synthesizes research-grade KV cache optimization, graph-based agent orchestration, and distributed cluster deployment into a unified system.
Active
Go
sovereign
Local-first AI operating system. No cloud. No telemetry. Your inference. Your memory. Your governance.
Production
Python
rlm
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
Active
Python
ollama-chatbot
Experimental Ollama integration for chatbot applications.
Experimental
Python