Sovereign AI engineering log
A self-hosted AI stack built and documented in public. Every article comes from a real system, a real error, or a real fix. Nothing is speculative.
For people running, scoping, or considering self-hosted LLMs on DGX Spark, Strix Halo, multi-3090, or similar hardware.
Who is cipherfox, why sovereign AI, and what the stack looks like right now.
Read about the projectAll articles ranked by EEAT quality score: expertise, experience, authority, trust.
View content quality
I ran Cloudflare's security-audit skill with a local Qwen3.6-35B on three of my own repositories, after a calibration on code with two known bugs. It found 5 real issues and missed most of the bugs I already knew about. What it is good for, and where it needs a reviewer.
Read article
An unattended A/B of six engine variants for Qwen3.6-35B on one DGX Spark: vLLM 0.23 against 0.32, Marlin against a native NVFP4 MoE kernel, async scheduling on and off, three MTP depths. Prefill got 51 percent faster, the native kernel lost, async scheduling bought nothing, and the safety net killed a test run.
Read article
GitHub's Project HydraFusion and HydraFusion Max route coding requests through Single, Cascade, and Critique patterns in the cloud. Sovereign Fleet runs those same three patterns unattended on your own Linux machine across Goose, Aider, Pi, and OpenCode inside a Landlock kernel sandbox.
Read article
I benchmarked goose, aider, Pi and opencode across 192 runs on a local Qwen3.6-35B. Aider passed 39 of 48 tasks at 3.0 minutes per correct result, while goose achieved 38 of 48 correct results at 1.6 minutes per correct result.
Read article
A coding agent delivered issue intake, a lane health check and three bug fixes for my agent fleet, with 179 green tests and the word verified. A review found a comment loop, a diagnosis that blamed the model for a directory bug, and behind that fix an engine bug that deleted the work of any agent that commits on its own.
Read article