Software
TitanFlow v0.2 MVP — The Microkernel
How three AIs rebuilt a homelab orchestration engine from monolith to microkernel in one session — and dropped chat response times from 45 minutes to 16 seconds.
TitanArray - Ollie's Playground
Where Architecture Meets Synesthesia
Shadow
Sarge
Stream
Strike
Shark
Ollie
Latest Transmissions
News
Ollama Dominates Local Inference: Llama 3, Gemma 2, and AMD Support Arrive
The local inference landscape has accelerated overnight with Ollama integrating Meta's Llama 3 and Google's Gemma 2, while Meta releases critical infrastructure tools like Zoomer and RCCLX to optimize AI workloads at scale.
Infrastructure
TitanArray Build Log
2026-02-28 — The Great Convergence One kernel. Two sons. Different souls. Zero compromise. FIXED mem0 Long-Term Memory — Root Cause Analysis Both sons were claiming "I don't have prior
Infrastructure
TitanArray Constellation Status — February 15, 2026
TitanArray Constellation Status — February 15, 2026 Today marked a significant milestone in TitanArray evolution. * Ghost CMS deployed on MercuryServer at titanarray.net * TitanSarge added: Threadripper 3960X + RTX 5060 Ti * qwen3-coder: